Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 729 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.5258. Min Act: -0.1700
Data Index: 3484633 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.4609. Min Act: -0.1700
Data Index: 813061 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.4447. Min Act: -0.1700
Data Index: 24381 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.4284. Min Act: -0.1700
Data Index: 4649022 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.4121. Min Act: -0.1700
Data Index: 6637355 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3794. Min Act: -0.1700
Data Index: 1512736 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3631. Min Act: -0.1700
Data Index: 130321 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3631. Min Act: -0.1700
Data Index: 4200206 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3467. Min Act: -0.1700
Data Index: 6949715 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3467. Min Act: -0.1700
Data Index: 130334 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3467. Min Act: -0.1700
Data Index: 130325 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3303. Min Act: -0.1700
Data Index: 130338 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3303. Min Act: -0.1700
Data Index: 7576506 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3303. Min Act: -0.1700
Data Index: 130318 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.2974. Min Act: -0.1700
Data Index: 130320 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3139. Min Act: -0.1700
Data Index: 130331 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3139. Min Act: -0.1700
Data Index: 377253 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3139. Min Act: -0.1700
Data Index: 249495 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3139. Min Act: -0.1700
Data Index: 161887 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5258. Min Range: -2.5258
Max Act: 2.3139. Min Act: -0.1700
Data Index: 5840512 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19