Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.4066. Min Act: -0.1700
Data Index: 5880736 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.3441. Min Act: -0.1700
Data Index: 6590651 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.2503. Min Act: -0.1700
Data Index: 4458290 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.2191. Min Act: -0.1700
Data Index: 3522179 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.2191. Min Act: -0.1700
Data Index: 8012299 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.1566. Min Act: -0.1700
Data Index: 539479 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.1566. Min Act: -0.1700
Data Index: 4355658 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.1253. Min Act: -0.1700
Data Index: 7241293 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.1566. Min Act: -0.1700
Data Index: 4909415 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.1253. Min Act: -0.1700
Data Index: 4372886 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.1253. Min Act: -0.1700
Data Index: 4157853 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.1253. Min Act: -0.1700
Data Index: 1897471 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.1253. Min Act: -0.1700
Data Index: 8510396 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.1253. Min Act: -0.1700
Data Index: 2488438 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.0941. Min Act: -0.1700
Data Index: 4909410 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.0628. Min Act: -0.1700
Data Index: 4749125 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.0941. Min Act: -0.1700
Data Index: 2254990 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.1253. Min Act: -0.1700
Data Index: 2847774 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.0941. Min Act: -0.1700
Data Index: 84736 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4066. Min Range: -4.4066
Max Act: 4.0941. Min Act: -0.1700
Data Index: 1182152 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19