Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 872 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.9711. Min Act: -0.1700
Data Index: 4151783 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.7836. Min Act: -0.1700
Data Index: 8016740 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.7524. Min Act: -0.1700
Data Index: 1442690 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.6586. Min Act: -0.1700
Data Index: 6972551 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.5649. Min Act: -0.1700
Data Index: 8250710 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.5961. Min Act: -0.1700
Data Index: 2258317 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.4399. Min Act: -0.1700
Data Index: 6106115 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.4399. Min Act: -0.1700
Data Index: 6332073 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.3774. Min Act: -0.1700
Data Index: 7241098 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.2524. Min Act: -0.1700
Data Index: 456455 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.2211. Min Act: -0.1700
Data Index: 3283133 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.2211. Min Act: -0.1700
Data Index: 2959019 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.1899. Min Act: -0.1700
Data Index: 6012129 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.1586. Min Act: -0.1700
Data Index: 8075693 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.1899. Min Act: -0.1700
Data Index: 2101051 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.1586. Min Act: -0.1700
Data Index: 2780675 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.1274. Min Act: -0.1700
Data Index: 2842237 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.0961. Min Act: -0.1700
Data Index: 262334 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.0961. Min Act: -0.1700
Data Index: 2709839 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9711. Min Range: -6.9711
Max Act: 6.0336. Min Act: -0.1700
Data Index: 7412547 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19