Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4177 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.5860. Min Act: -0.1700
Data Index: 5470492 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.5860. Min Act: -0.1700
Data Index: 3411152 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.5548. Min Act: -0.1700
Data Index: 6680160 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.4923. Min Act: -0.1700
Data Index: 2393564 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.3360. Min Act: -0.1700
Data Index: 7105790 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.2735. Min Act: -0.1700
Data Index: 3675932 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.2422. Min Act: -0.1700
Data Index: 5708422 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.2735. Min Act: -0.1700
Data Index: 2237046 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.2110. Min Act: -0.1700
Data Index: 7418470 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.2110. Min Act: -0.1700
Data Index: 1165538 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1797. Min Act: -0.1700
Data Index: 7182270 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1485. Min Act: -0.1700
Data Index: 637502 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1485. Min Act: -0.1700
Data Index: 8175619 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1797. Min Act: -0.1700
Data Index: 8584935 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1485. Min Act: -0.1700
Data Index: 4697774 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1172. Min Act: -0.1700
Data Index: 1138922 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1172. Min Act: -0.1700
Data Index: 5111188 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1172. Min Act: -0.1700
Data Index: 7489195 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.1172. Min Act: -0.1700
Data Index: 7580341 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5860. Min Range: -4.5860
Max Act: 4.0547. Min Act: -0.1700
Data Index: 5502410 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19