Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3700 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.6840. Min Act: -0.1700
Data Index: 4063212 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.6684. Min Act: -0.1700
Data Index: 7394558 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.6371. Min Act: -0.1700
Data Index: 4249833 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.6214. Min Act: -0.1700
Data Index: 3539700 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.6214. Min Act: -0.1700
Data Index: 3893303 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.6214. Min Act: -0.1700
Data Index: 3426671 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5901. Min Act: -0.1700
Data Index: 4581180 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5901. Min Act: -0.1700
Data Index: 5334500 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5901. Min Act: -0.1700
Data Index: 1956971 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5901. Min Act: -0.1700
Data Index: 3398960 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5901. Min Act: -0.1700
Data Index: 754519 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5901. Min Act: -0.1700
Data Index: 2215961 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5901. Min Act: -0.1700
Data Index: 3882697 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.6058. Min Act: -0.1700
Data Index: 281603 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5901. Min Act: -0.1700
Data Index: 3224814 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5745. Min Act: -0.1700
Data Index: 121284 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5901. Min Act: -0.1700
Data Index: 6536166 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5901. Min Act: -0.1700
Data Index: 6063842 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5588. Min Act: -0.1700
Data Index: 8783055 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6840. Min Range: -3.6840
Max Act: 3.5745. Min Act: -0.1700
Data Index: 2158633 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19