Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1277 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3418. Min Range: -5.3418
Max Act: 5.3418. Min Act: -0.1700
Data Index: 7754066 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3418. Min Range: -5.3418
Max Act: 5.1230. Min Act: -0.1700
Data Index: 4370210 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3418. Min Range: -5.3418
Max Act: 5.0605. Min Act: -0.1700
Data Index: 1798426 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3418. Min Range: -5.3418
Max Act: 5.0293. Min Act: -0.1700
Data Index: 8230187 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3418. Min Range: -5.3418
Max Act: 5.0918. Min Act: -0.1700
Data Index: 3007056 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9980. Min Act: -0.1700
Data Index: 6552943 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3418. Min Range: -5.3418
Max Act: 5.0293. Min Act: -0.1700
Data Index: 4752637 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9980. Min Act: -0.1700
Data Index: 6450186 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9355. Min Act: -0.1700
Data Index: 107896 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9980. Min Act: -0.1700
Data Index: 7977068 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9980. Min Act: -0.1700
Data Index: 5043894 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9668. Min Act: -0.1700
Data Index: 7694505 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9668. Min Act: -0.1700
Data Index: 5182511 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9668. Min Act: -0.1700
Data Index: 7046712 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9980. Min Act: -0.1700
Data Index: 4789080 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9668. Min Act: -0.1700
Data Index: 1881217 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9355. Min Act: -0.1700
Data Index: 7818138 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9668. Min Act: -0.1700
Data Index: 8241096 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9355. Min Act: -0.1700
Data Index: 320559 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3418. Min Range: -5.3418
Max Act: 4.9355. Min Act: -0.1700
Data Index: 6767311 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19