Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3981 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.7396. Min Act: -0.1700
Data Index: 7126231 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.6458. Min Act: -0.1700
Data Index: 1810569 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5988. Min Act: -0.1700
Data Index: 5745525 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5988. Min Act: -0.1700
Data Index: 4540275 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5832. Min Act: -0.1700
Data Index: 8704207 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5675. Min Act: -0.1700
Data Index: 3347046 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5675. Min Act: -0.1700
Data Index: 5933849 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5519. Min Act: -0.1700
Data Index: 8698299 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5362. Min Act: -0.1700
Data Index: 2908304 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5205. Min Act: -0.1700
Data Index: 22348 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5519. Min Act: -0.1700
Data Index: 4656370 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5362. Min Act: -0.1700
Data Index: 3456317 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5205. Min Act: -0.1700
Data Index: 8619020 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5362. Min Act: -0.1700
Data Index: 6174678 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5205. Min Act: -0.1700
Data Index: 7028166 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5205. Min Act: -0.1700
Data Index: 330978 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5049. Min Act: -0.1700
Data Index: 5130080 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5049. Min Act: -0.1700
Data Index: 2354579 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.5049. Min Act: -0.1700
Data Index: 4540270 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7396. Min Range: -3.7396
Max Act: 3.4892. Min Act: -0.1700
Data Index: 782464 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19