Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 706 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3566. Min Range: -8.3566
Max Act: 8.3566. Min Act: -0.1700
Data Index: 4976758 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3566. Min Range: -8.3566
Max Act: 8.2941. Min Act: -0.1700
Data Index: 4502580 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3566. Min Range: -8.3566
Max Act: 8.2316. Min Act: -0.1700
Data Index: 1688321 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3566. Min Range: -8.3566
Max Act: 8.1691. Min Act: -0.1700
Data Index: 2418877 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3566. Min Range: -8.3566
Max Act: 8.2316. Min Act: -0.1700
Data Index: 5842081 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3566. Min Range: -8.3566
Max Act: 8.1691. Min Act: -0.1700
Data Index: 1716818 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3566. Min Range: -8.3566
Max Act: 8.1691. Min Act: -0.1700
Data Index: 3405118 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3566. Min Range: -8.3566
Max Act: 8.1691. Min Act: -0.1700
Data Index: 5994882 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3566. Min Range: -8.3566
Max Act: 8.1066. Min Act: -0.1700
Data Index: 4731509 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3566. Min Range: -8.3566
Max Act: 8.1066. Min Act: -0.1700
Data Index: 6041075 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3566. Min Range: -8.3566
Max Act: 8.1066. Min Act: -0.1700
Data Index: 1069626 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3566. Min Range: -8.3566
Max Act: 8.0441. Min Act: -0.1700
Data Index: 6336832 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3566. Min Range: -8.3566
Max Act: 7.9816. Min Act: -0.1700
Data Index: 734802 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3566. Min Range: -8.3566
Max Act: 7.9191. Min Act: -0.1700
Data Index: 6966317 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3566. Min Range: -8.3566
Max Act: 7.8878. Min Act: -0.1700
Data Index: 8762749 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3566. Min Range: -8.3566
Max Act: 7.8566. Min Act: -0.1700
Data Index: 6252272 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3566. Min Range: -8.3566
Max Act: 7.8566. Min Act: -0.1700
Data Index: 1273785 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3566. Min Range: -8.3566
Max Act: 7.8566. Min Act: -0.1700
Data Index: 4348405 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3566. Min Range: -8.3566
Max Act: 7.8566. Min Act: -0.1700
Data Index: 8546783 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3566. Min Range: -8.3566
Max Act: 7.8253. Min Act: -0.1700
Data Index: 6591586 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19