Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3871 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0811. Min Range: -7.0811
Max Act: 7.0811. Min Act: -0.1700
Data Index: 6097090 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.3623. Min Act: -0.1700
Data Index: 6500659 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.2686. Min Act: -0.1700
Data Index: 4988989 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.2061. Min Act: -0.1700
Data Index: 10355 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.2061. Min Act: -0.1700
Data Index: 242987 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.1436. Min Act: -0.1700
Data Index: 2446995 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.1436. Min Act: -0.1700
Data Index: 1887401 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.1436. Min Act: -0.1700
Data Index: 5671162 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.1123. Min Act: -0.1700
Data Index: 7147700 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.0811. Min Act: -0.1700
Data Index: 1592181 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.0498. Min Act: -0.1700
Data Index: 6806105 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.0498. Min Act: -0.1700
Data Index: 6322104 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.0811. Min Act: -0.1700
Data Index: 93094 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.0186. Min Act: -0.1700
Data Index: 8602984 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.0186. Min Act: -0.1700
Data Index: 6660090 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0811. Min Range: -7.0811
Max Act: 6.0186. Min Act: -0.1700
Data Index: 3541428 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0811. Min Range: -7.0811
Max Act: 5.9873. Min Act: -0.1700
Data Index: 1781774 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0811. Min Range: -7.0811
Max Act: 5.9561. Min Act: -0.1700
Data Index: 6538035 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0811. Min Range: -7.0811
Max Act: 5.9561. Min Act: -0.1700
Data Index: 250320 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0811. Min Range: -7.0811
Max Act: 5.9561. Min Act: -0.1700
Data Index: 5026488 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19