Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2606 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2182. Min Range: -3.2182
Max Act: 3.2182. Min Act: -0.1700
Data Index: 483605 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2182. Min Range: -3.2182
Max Act: 3.1238. Min Act: -0.1700
Data Index: 4486964 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2182. Min Range: -3.2182
Max Act: 3.0922. Min Act: -0.1700
Data Index: 5957330 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2182. Min Range: -3.2182
Max Act: 3.0922. Min Act: -0.1700
Data Index: 2112177 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2182. Min Range: -3.2182
Max Act: 3.0607. Min Act: -0.1700
Data Index: 5880410 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2182. Min Range: -3.2182
Max Act: 3.0607. Min Act: -0.1700
Data Index: 1549017 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2182. Min Range: -3.2182
Max Act: 3.0291. Min Act: -0.1700
Data Index: 1718091 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2182. Min Range: -3.2182
Max Act: 3.0449. Min Act: -0.1700
Data Index: 1119350 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2182. Min Range: -3.2182
Max Act: 3.0607. Min Act: -0.1700
Data Index: 7210503 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2182. Min Range: -3.2182
Max Act: 3.0449. Min Act: -0.1700
Data Index: 4204569 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2182. Min Range: -3.2182
Max Act: 2.9975. Min Act: -0.1700
Data Index: 6740937 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2182. Min Range: -3.2182
Max Act: 2.9975. Min Act: -0.1700
Data Index: 3475673 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2182. Min Range: -3.2182
Max Act: 2.9817. Min Act: -0.1700
Data Index: 1556894 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2182. Min Range: -3.2182
Max Act: 2.9975. Min Act: -0.1700
Data Index: 6954077 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2182. Min Range: -3.2182
Max Act: 2.9975. Min Act: -0.1700
Data Index: 7469871 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2182. Min Range: -3.2182
Max Act: 2.9659. Min Act: -0.1700
Data Index: 3461490 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2182. Min Range: -3.2182
Max Act: 2.9343. Min Act: -0.1700
Data Index: 2496889 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2182. Min Range: -3.2182
Max Act: 2.9343. Min Act: -0.1700
Data Index: 4074829 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2182. Min Range: -3.2182
Max Act: 2.9343. Min Act: -0.1700
Data Index: 133843 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2182. Min Range: -3.2182
Max Act: 2.9501. Min Act: -0.1700
Data Index: 7879800 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19