Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2285 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2523. Min Range: -7.2523
Max Act: 7.2523. Min Act: -0.1700
Data Index: 761619 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2523. Min Range: -7.2523
Max Act: 7.0023. Min Act: -0.1700
Data Index: 6627906 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.9085. Min Act: -0.1700
Data Index: 8492153 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.8773. Min Act: -0.1700
Data Index: 379134 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.6898. Min Act: -0.1700
Data Index: 659030 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.7210. Min Act: -0.1700
Data Index: 1027308 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.6585. Min Act: -0.1700
Data Index: 3186489 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.6585. Min Act: -0.1700
Data Index: 6869341 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.6273. Min Act: -0.1700
Data Index: 5044121 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.6273. Min Act: -0.1700
Data Index: 8591498 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.5648. Min Act: -0.1700
Data Index: 7329143 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.5335. Min Act: -0.1700
Data Index: 5322645 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.5335. Min Act: -0.1700
Data Index: 208915 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.5023. Min Act: -0.1700
Data Index: 2262345 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.4710. Min Act: -0.1700
Data Index: 6033485 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.4710. Min Act: -0.1700
Data Index: 6385683 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.4398. Min Act: -0.1700
Data Index: 7313388 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.4398. Min Act: -0.1700
Data Index: 3888870 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.4085. Min Act: -0.1700
Data Index: 982881 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2523. Min Range: -7.2523
Max Act: 6.4398. Min Act: -0.1700
Data Index: 4709864 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19