Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4842 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.4618. Min Act: -0.1700
Data Index: 6391766 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.1180. Min Act: -0.1700
Data Index: 4443404 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.0555. Min Act: -0.1700
Data Index: 1988994 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.0555. Min Act: -0.1700
Data Index: 2724711 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.0243. Min Act: -0.1700
Data Index: 7629340 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.9930. Min Act: -0.1700
Data Index: 2287777 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.9305. Min Act: -0.1700
Data Index: 7630588 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.9305. Min Act: -0.1700
Data Index: 6594216 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.9305. Min Act: -0.1700
Data Index: 8244776 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.8993. Min Act: -0.1700
Data Index: 1052099 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.8680. Min Act: -0.1700
Data Index: 3650537 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.8680. Min Act: -0.1700
Data Index: 2286706 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.8368. Min Act: -0.1700
Data Index: 1771162 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.8368. Min Act: -0.1700
Data Index: 3228170 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.8055. Min Act: -0.1700
Data Index: 5398427 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.8368. Min Act: -0.1700
Data Index: 8301752 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.7743. Min Act: -0.1700
Data Index: 5789497 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.7743. Min Act: -0.1700
Data Index: 5807354 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.7743. Min Act: -0.1700
Data Index: 3224312 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4618. Min Range: -6.4618
Max Act: 5.7430. Min Act: -0.1700
Data Index: 6047731 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19