Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3539 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.5943. Min Act: -0.1700
Data Index: 3191683 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.6255. Min Act: -0.1700
Data Index: 5131133 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.5630. Min Act: -0.1700
Data Index: 426750 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.2818. Min Act: -0.1700
Data Index: 7106839 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.2505. Min Act: -0.1700
Data Index: 4347244 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.2193. Min Act: -0.1700
Data Index: 6588719 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.2193. Min Act: -0.1700
Data Index: 4224748 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.1880. Min Act: -0.1700
Data Index: 5954204 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.2193. Min Act: -0.1700
Data Index: 960189 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.1880. Min Act: -0.1700
Data Index: 2592016 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.2193. Min Act: -0.1700
Data Index: 1018638 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.1568. Min Act: -0.1700
Data Index: 2601990 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.1568. Min Act: -0.1700
Data Index: 3898376 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.1255. Min Act: -0.1700
Data Index: 8398139 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.0943. Min Act: -0.1700
Data Index: 119345 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.0630. Min Act: -0.1700
Data Index: 8342407 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.0630. Min Act: -0.1700
Data Index: 3373439 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.0005. Min Act: -0.1700
Data Index: 2588664 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.0630. Min Act: -0.1700
Data Index: 1412591 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6255. Min Range: -7.6255
Max Act: 7.0005. Min Act: -0.1700
Data Index: 823718 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19