Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2218 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.2136. Min Range: -4.2136
Max Act: 4.2136. Min Act: -0.1700
Data Index: 7485648 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2136. Min Range: -4.2136
Max Act: 4.1199. Min Act: -0.1700
Data Index: 8568091 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2136. Min Range: -4.2136
Max Act: 4.0886. Min Act: -0.1700
Data Index: 4195994 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2136. Min Range: -4.2136
Max Act: 4.0261. Min Act: -0.1700
Data Index: 6089692 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2136. Min Range: -4.2136
Max Act: 4.0261. Min Act: -0.1700
Data Index: 1088786 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2136. Min Range: -4.2136
Max Act: 4.0574. Min Act: -0.1700
Data Index: 8011146 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2136. Min Range: -4.2136
Max Act: 4.0574. Min Act: -0.1700
Data Index: 3833139 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9948. Min Act: -0.1700
Data Index: 8541554 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9948. Min Act: -0.1700
Data Index: 6367646 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9636. Min Act: -0.1700
Data Index: 3954300 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9323. Min Act: -0.1700
Data Index: 1630862 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9636. Min Act: -0.1700
Data Index: 6515534 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9323. Min Act: -0.1700
Data Index: 1122323 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9011. Min Act: -0.1700
Data Index: 3783578 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9323. Min Act: -0.1700
Data Index: 1199159 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9011. Min Act: -0.1700
Data Index: 4524068 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8698. Min Act: -0.1700
Data Index: 6480377 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9011. Min Act: -0.1700
Data Index: 4012869 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8698. Min Act: -0.1700
Data Index: 1543075 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8698. Min Act: -0.1700
Data Index: 3554240 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19