Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2172 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2943. Min Range: -6.2943
Max Act: 6.2943. Min Act: -0.1700
Data Index: 335644 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.9818. Min Act: -0.1700
Data Index: 3825327 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.8568. Min Act: -0.1700
Data Index: 7460863 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.8256. Min Act: -0.1700
Data Index: 4334587 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.8256. Min Act: -0.1700
Data Index: 5891814 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.7631. Min Act: -0.1700
Data Index: 7050858 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.7318. Min Act: -0.1700
Data Index: 4427564 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.7318. Min Act: -0.1700
Data Index: 2211839 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.7318. Min Act: -0.1700
Data Index: 6431184 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.7318. Min Act: -0.1700
Data Index: 1480936 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.7318. Min Act: -0.1700
Data Index: 2572038 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.7318. Min Act: -0.1700
Data Index: 4581427 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.7318. Min Act: -0.1700
Data Index: 2313397 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.7006. Min Act: -0.1700
Data Index: 7367426 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.7006. Min Act: -0.1700
Data Index: 2510359 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.7006. Min Act: -0.1700
Data Index: 3198474 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.6693. Min Act: -0.1700
Data Index: 6743418 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.6693. Min Act: -0.1700
Data Index: 3673350 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.6693. Min Act: -0.1700
Data Index: 361065 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2943. Min Range: -6.2943
Max Act: 5.6693. Min Act: -0.1700
Data Index: 2053364 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19