Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5465 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8381. Min Range: -12.8381
Max Act: 12.8381. Min Act: -0.1700
Data Index: 2824360 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8381. Min Range: -12.8381
Max Act: 12.5881. Min Act: -0.1700
Data Index: 1632931 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8381. Min Range: -12.8381
Max Act: 12.4631. Min Act: -0.1700
Data Index: 3636242 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8381. Min Range: -12.8381
Max Act: 12.0881. Min Act: -0.1700
Data Index: 2047581 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8381. Min Range: -12.8381
Max Act: 12.0881. Min Act: -0.1700
Data Index: 3238522 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8381. Min Range: -12.8381
Max Act: 12.0881. Min Act: -0.1700
Data Index: 2075111 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8381. Min Range: -12.8381
Max Act: 12.0881. Min Act: -0.1700
Data Index: 3576463 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.9631. Min Act: -0.1700
Data Index: 5512159 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.9631. Min Act: -0.1700
Data Index: 3084064 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.9006. Min Act: -0.1700
Data Index: 2939218 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.9006. Min Act: -0.1700
Data Index: 441414 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.7756. Min Act: -0.1700
Data Index: 8102989 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.7756. Min Act: -0.1700
Data Index: 8529699 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.6506. Min Act: -0.1700
Data Index: 2647318 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.6506. Min Act: -0.1700
Data Index: 2166160 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.5881. Min Act: -0.1700
Data Index: 8313818 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.5881. Min Act: -0.1700
Data Index: 3692344 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.6506. Min Act: -0.1700
Data Index: 7334482 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.5881. Min Act: -0.1700
Data Index: 7848214 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8381. Min Range: -12.8381
Max Act: 11.5256. Min Act: -0.1700
Data Index: 6975990 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19