Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1706 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.6521. Min Act: -0.1700
Data Index: 4970876 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.3702. Min Act: -0.1700
Data Index: 1573343 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.3231. Min Act: -0.1700
Data Index: 7849626 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.2760. Min Act: -0.1700
Data Index: 389861 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.2760. Min Act: -0.1700
Data Index: 182810 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.2603. Min Act: -0.1700
Data Index: 18688 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.2289. Min Act: -0.1700
Data Index: 81066 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1974. Min Act: -0.1700
Data Index: 7055603 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1974. Min Act: -0.1700
Data Index: 6182340 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1817. Min Act: -0.1700
Data Index: 1209583 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1817. Min Act: -0.1700
Data Index: 5073730 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1817. Min Act: -0.1700
Data Index: 1267775 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1817. Min Act: -0.1700
Data Index: 435500 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1817. Min Act: -0.1700
Data Index: 1486036 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1660. Min Act: -0.1700
Data Index: 7512004 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1660. Min Act: -0.1700
Data Index: 5213354 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1660. Min Act: -0.1700
Data Index: 4092560 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1502. Min Act: -0.1700
Data Index: 3272065 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1345. Min Act: -0.1700
Data Index: 7652049 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6521. Min Range: -3.6521
Max Act: 3.1502. Min Act: -0.1700
Data Index: 4260308 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19