Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3162 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.8666. Min Act: -0.1700
Data Index: 6462337 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.6478. Min Act: -0.1700
Data Index: 2210760 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.5228. Min Act: -0.1700
Data Index: 2769580 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.4603. Min Act: -0.1700
Data Index: 1462355 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.4603. Min Act: -0.1700
Data Index: 123697 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.4603. Min Act: -0.1700
Data Index: 4251499 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.3978. Min Act: -0.1700
Data Index: 8807249 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.3978. Min Act: -0.1700
Data Index: 7765458 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.3978. Min Act: -0.1700
Data Index: 2499452 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.3353. Min Act: -0.1700
Data Index: 1564080 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.3353. Min Act: -0.1700
Data Index: 4304521 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.3353. Min Act: -0.1700
Data Index: 6584600 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.3353. Min Act: -0.1700
Data Index: 8495665 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.3041. Min Act: -0.1700
Data Index: 2262446 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.2728. Min Act: -0.1700
Data Index: 1119595 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.3041. Min Act: -0.1700
Data Index: 8417742 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.2728. Min Act: -0.1700
Data Index: 8794319 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.2728. Min Act: -0.1700
Data Index: 1647098 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.2728. Min Act: -0.1700
Data Index: 6165732 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8666. Min Range: -7.8666
Max Act: 7.2103. Min Act: -0.1700
Data Index: 8357142 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19