Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.4276. Min Act: -0.1700
Data Index: 5538866 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.3026. Min Act: -0.1700
Data Index: 6216310 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.3026. Min Act: -0.1700
Data Index: 7953830 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.2401. Min Act: -0.1700
Data Index: 8373162 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.1776. Min Act: -0.1700
Data Index: 6129389 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.1776. Min Act: -0.1700
Data Index: 1497854 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.1776. Min Act: -0.1700
Data Index: 166416 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.1151. Min Act: -0.1700
Data Index: 8445637 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.0526. Min Act: -0.1700
Data Index: 820631 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.0526. Min Act: -0.1700
Data Index: 4466039 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.0526. Min Act: -0.1700
Data Index: 4717358 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.0526. Min Act: -0.1700
Data Index: 826858 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4276. Min Range: -8.4276
Max Act: 8.0526. Min Act: -0.1700
Data Index: 1884068 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4276. Min Range: -8.4276
Max Act: 7.9901. Min Act: -0.1700
Data Index: 1418992 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4276. Min Range: -8.4276
Max Act: 7.9901. Min Act: -0.1700
Data Index: 7649714 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4276. Min Range: -8.4276
Max Act: 7.9901. Min Act: -0.1700
Data Index: 2685169 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4276. Min Range: -8.4276
Max Act: 7.9901. Min Act: -0.1700
Data Index: 8511193 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4276. Min Range: -8.4276
Max Act: 7.9901. Min Act: -0.1700
Data Index: 4506401 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4276. Min Range: -8.4276
Max Act: 7.9901. Min Act: -0.1700
Data Index: 6596241 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4276. Min Range: -8.4276
Max Act: 7.9276. Min Act: -0.1700
Data Index: 3370782 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19