Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 66 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6073. Min Range: -5.6073
Max Act: 5.6073. Min Act: -0.1700
Data Index: 715235 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6073. Min Range: -5.6073
Max Act: 5.4823. Min Act: -0.1700
Data Index: 348526 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6073. Min Range: -5.6073
Max Act: 5.2635. Min Act: -0.1700
Data Index: 3957185 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6073. Min Range: -5.6073
Max Act: 5.2323. Min Act: -0.1700
Data Index: 715236 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6073. Min Range: -5.6073
Max Act: 5.2635. Min Act: -0.1700
Data Index: 6911195 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6073. Min Range: -5.6073
Max Act: 5.2010. Min Act: -0.1700
Data Index: 8581137 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6073. Min Range: -5.6073
Max Act: 5.2010. Min Act: -0.1700
Data Index: 6650639 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6073. Min Range: -5.6073
Max Act: 5.1385. Min Act: -0.1700
Data Index: 3000295 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6073. Min Range: -5.6073
Max Act: 5.1385. Min Act: -0.1700
Data Index: 3476262 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6073. Min Range: -5.6073
Max Act: 5.1073. Min Act: -0.1700
Data Index: 2189483 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6073. Min Range: -5.6073
Max Act: 5.0135. Min Act: -0.1700
Data Index: 846489 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6073. Min Range: -5.6073
Max Act: 5.0135. Min Act: -0.1700
Data Index: 7480351 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6073. Min Range: -5.6073
Max Act: 4.9823. Min Act: -0.1700
Data Index: 8431048 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6073. Min Range: -5.6073
Max Act: 4.9198. Min Act: -0.1700
Data Index: 6242181 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6073. Min Range: -5.6073
Max Act: 4.9198. Min Act: -0.1700
Data Index: 3986548 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6073. Min Range: -5.6073
Max Act: 4.9198. Min Act: -0.1700
Data Index: 3421617 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6073. Min Range: -5.6073
Max Act: 4.9198. Min Act: -0.1700
Data Index: 8462619 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6073. Min Range: -5.6073
Max Act: 4.9198. Min Act: -0.1700
Data Index: 7672032 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6073. Min Range: -5.6073
Max Act: 4.8885. Min Act: -0.1700
Data Index: 1075729 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6073. Min Range: -5.6073
Max Act: 4.8573. Min Act: -0.1700
Data Index: 3779671 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19