Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 962 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.5958. Min Act: -0.1700
Data Index: 6161978 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.5176. Min Act: -0.1700
Data Index: 5756894 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.5019. Min Act: -0.1700
Data Index: 8131059 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.5019. Min Act: -0.1700
Data Index: 1698449 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.5019. Min Act: -0.1700
Data Index: 7405240 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.5176. Min Act: -0.1700
Data Index: 2341294 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.4549. Min Act: -0.1700
Data Index: 4826646 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.4392. Min Act: -0.1700
Data Index: 4092687 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.4706. Min Act: -0.1700
Data Index: 4954970 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.4392. Min Act: -0.1700
Data Index: 7518998 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.4236. Min Act: -0.1700
Data Index: 3197583 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.4236. Min Act: -0.1700
Data Index: 8368201 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.4079. Min Act: -0.1700
Data Index: 6214481 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.4236. Min Act: -0.1700
Data Index: 8131058 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.4079. Min Act: -0.1700
Data Index: 3549786 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.4079. Min Act: -0.1700
Data Index: 2232995 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.3922. Min Act: -0.1700
Data Index: 5674700 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.4079. Min Act: -0.1700
Data Index: 6028219 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.3765. Min Act: -0.1700
Data Index: 5716241 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5958. Min Range: -3.5958
Max Act: 3.3765. Min Act: -0.1700
Data Index: 5853193 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19