Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 651 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.5166. Min Act: -0.1700
Data Index: 2605462 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.3916. Min Act: -0.1700
Data Index: 3435322 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.2666. Min Act: -0.1700
Data Index: 4649998 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.2041. Min Act: -0.1700
Data Index: 4326631 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.2666. Min Act: -0.1700
Data Index: 2233192 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.2041. Min Act: -0.1700
Data Index: 6955631 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.1416. Min Act: -0.1700
Data Index: 7744571 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.2041. Min Act: -0.1700
Data Index: 1222076 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.1416. Min Act: -0.1700
Data Index: 8292215 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.0791. Min Act: -0.1700
Data Index: 3549796 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.0791. Min Act: -0.1700
Data Index: 4518731 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.0791. Min Act: -0.1700
Data Index: 2924868 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.0791. Min Act: -0.1700
Data Index: 493187 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.0166. Min Act: -0.1700
Data Index: 3018386 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.0166. Min Act: -0.1700
Data Index: 5511111 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5166. Min Range: -11.5166
Max Act: 11.0166. Min Act: -0.1700
Data Index: 6598006 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5166. Min Range: -11.5166
Max Act: 10.9541. Min Act: -0.1700
Data Index: 1863859 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5166. Min Range: -11.5166
Max Act: 10.9541. Min Act: -0.1700
Data Index: 2669734 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5166. Min Range: -11.5166
Max Act: 10.9541. Min Act: -0.1700
Data Index: 6487498 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5166. Min Range: -11.5166
Max Act: 10.9541. Min Act: -0.1700
Data Index: 4055811 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19