Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1566 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.9478. Min Act: -0.1700
Data Index: 5163688 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.8541. Min Act: -0.1700
Data Index: 4532001 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.8228. Min Act: -0.1700
Data Index: 6618121 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.7291. Min Act: -0.1700
Data Index: 8219427 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.7291. Min Act: -0.1700
Data Index: 2640052 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.6666. Min Act: -0.1700
Data Index: 7482036 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.6978. Min Act: -0.1700
Data Index: 3771954 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.7291. Min Act: -0.1700
Data Index: 7482035 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.6666. Min Act: -0.1700
Data Index: 8648178 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.6666. Min Act: -0.1700
Data Index: 6755309 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.6353. Min Act: -0.1700
Data Index: 4913636 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.5728. Min Act: -0.1700
Data Index: 1302 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.5728. Min Act: -0.1700
Data Index: 1950803 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.6041. Min Act: -0.1700
Data Index: 3910410 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.6041. Min Act: -0.1700
Data Index: 8219425 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.6353. Min Act: -0.1700
Data Index: 7482040 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.6041. Min Act: -0.1700
Data Index: 6006822 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.6041. Min Act: -0.1700
Data Index: 1873740 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.5728. Min Act: -0.1700
Data Index: 2640046 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9478. Min Range: -6.9478
Max Act: 6.5728. Min Act: -0.1700
Data Index: 4144907 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19