Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1288 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.5979. Min Act: -0.1700
Data Index: 1189345 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.4104. Min Act: -0.1700
Data Index: 3428655 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.2541. Min Act: -0.1700
Data Index: 4252886 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.2854. Min Act: -0.1700
Data Index: 7663529 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.1291. Min Act: -0.1700
Data Index: 4333945 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.0979. Min Act: -0.1700
Data Index: 8831442 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.0666. Min Act: -0.1700
Data Index: 4074134 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.0666. Min Act: -0.1700
Data Index: 6233653 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.0979. Min Act: -0.1700
Data Index: 7878982 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.0666. Min Act: -0.1700
Data Index: 2389757 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.0666. Min Act: -0.1700
Data Index: 2927336 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.0666. Min Act: -0.1700
Data Index: 8105697 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.0041. Min Act: -0.1700
Data Index: 8153815 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5979. Min Range: -6.5979
Max Act: 5.9729. Min Act: -0.1700
Data Index: 396827 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5979. Min Range: -6.5979
Max Act: 6.0041. Min Act: -0.1700
Data Index: 5933019 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5979. Min Range: -6.5979
Max Act: 5.9729. Min Act: -0.1700
Data Index: 3393994 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5979. Min Range: -6.5979
Max Act: 5.9729. Min Act: -0.1700
Data Index: 2964886 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5979. Min Range: -6.5979
Max Act: 5.9729. Min Act: -0.1700
Data Index: 6965642 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5979. Min Range: -6.5979
Max Act: 5.9729. Min Act: -0.1700
Data Index: 2536914 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5979. Min Range: -6.5979
Max Act: 5.9416. Min Act: -0.1700
Data Index: 6319148 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19