Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 597 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.6523. Min Act: -0.1700
Data Index: 1433221 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.6211. Min Act: -0.1700
Data Index: 5788472 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.4961. Min Act: -0.1700
Data Index: 372912 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.4961. Min Act: -0.1700
Data Index: 5861184 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.4648. Min Act: -0.1700
Data Index: 6507343 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.4648. Min Act: -0.1700
Data Index: 2592283 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.4336. Min Act: -0.1700
Data Index: 4643390 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.4023. Min Act: -0.1700
Data Index: 4827627 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.4023. Min Act: -0.1700
Data Index: 5331032 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.4023. Min Act: -0.1700
Data Index: 2108342 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.4023. Min Act: -0.1700
Data Index: 3874304 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.3711. Min Act: -0.1700
Data Index: 8754334 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.3711. Min Act: -0.1700
Data Index: 5119238 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.3398. Min Act: -0.1700
Data Index: 811835 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.3086. Min Act: -0.1700
Data Index: 806378 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.3086. Min Act: -0.1700
Data Index: 124743 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.3086. Min Act: -0.1700
Data Index: 5411279 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.3086. Min Act: -0.1700
Data Index: 8374656 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.3086. Min Act: -0.1700
Data Index: 2106864 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6523. Min Range: -6.6523
Max Act: 6.3086. Min Act: -0.1700
Data Index: 1626634 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19