Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1367 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.9820. Min Act: -0.1700
Data Index: 6979374 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.7320. Min Act: -0.1700
Data Index: 5976699 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.7320. Min Act: -0.1700
Data Index: 6864546 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.7008. Min Act: -0.1700
Data Index: 470769 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.5445. Min Act: -0.1700
Data Index: 2251388 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.4820. Min Act: -0.1700
Data Index: 2292066 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.4820. Min Act: -0.1700
Data Index: 2583871 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.5133. Min Act: -0.1700
Data Index: 8673419 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.4820. Min Act: -0.1700
Data Index: 2876538 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.4508. Min Act: -0.1700
Data Index: 5158858 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.4508. Min Act: -0.1700
Data Index: 6249825 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.4508. Min Act: -0.1700
Data Index: 4955524 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.4508. Min Act: -0.1700
Data Index: 8550418 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.4195. Min Act: -0.1700
Data Index: 8551381 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.4195. Min Act: -0.1700
Data Index: 2457927 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.3883. Min Act: -0.1700
Data Index: 8831355 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.3570. Min Act: -0.1700
Data Index: 1794801 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.3883. Min Act: -0.1700
Data Index: 3722874 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.3570. Min Act: -0.1700
Data Index: 5775231 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9820. Min Range: -6.9820
Max Act: 6.3570. Min Act: -0.1700
Data Index: 4041622 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19