Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8114. Min Range: -6.8114
Max Act: 6.8114. Min Act: -0.1700
Data Index: 6267180 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8114. Min Range: -6.8114
Max Act: 6.4677. Min Act: -0.1700
Data Index: 1009357 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8114. Min Range: -6.8114
Max Act: 6.3427. Min Act: -0.1700
Data Index: 8224981 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8114. Min Range: -6.8114
Max Act: 6.1552. Min Act: -0.1700
Data Index: 1114150 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8114. Min Range: -6.8114
Max Act: 6.0927. Min Act: -0.1700
Data Index: 8548784 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8114. Min Range: -6.8114
Max Act: 6.1239. Min Act: -0.1700
Data Index: 7100222 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8114. Min Range: -6.8114
Max Act: 6.0927. Min Act: -0.1700
Data Index: 6381317 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8114. Min Range: -6.8114
Max Act: 6.0927. Min Act: -0.1700
Data Index: 3411424 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8114. Min Range: -6.8114
Max Act: 6.0927. Min Act: -0.1700
Data Index: 5481334 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8114. Min Range: -6.8114
Max Act: 6.0302. Min Act: -0.1700
Data Index: 1850129 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8114. Min Range: -6.8114
Max Act: 5.9989. Min Act: -0.1700
Data Index: 1873033 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8114. Min Range: -6.8114
Max Act: 5.9989. Min Act: -0.1700
Data Index: 3137964 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8114. Min Range: -6.8114
Max Act: 5.9677. Min Act: -0.1700
Data Index: 392619 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8114. Min Range: -6.8114
Max Act: 5.9989. Min Act: -0.1700
Data Index: 7655504 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8114. Min Range: -6.8114
Max Act: 5.9677. Min Act: -0.1700
Data Index: 1244011 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8114. Min Range: -6.8114
Max Act: 5.9364. Min Act: -0.1700
Data Index: 1356634 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8114. Min Range: -6.8114
Max Act: 5.9989. Min Act: -0.1700
Data Index: 1099671 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8114. Min Range: -6.8114
Max Act: 5.9364. Min Act: -0.1700
Data Index: 4883678 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8114. Min Range: -6.8114
Max Act: 5.9989. Min Act: -0.1700
Data Index: 514053 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8114. Min Range: -6.8114
Max Act: 5.9052. Min Act: -0.1700
Data Index: 3034768 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19