Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.3638. Min Act: -0.1700
Data Index: 6198740 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.3010. Min Act: -0.1700
Data Index: 1921761 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.2853. Min Act: -0.1700
Data Index: 6361096 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.2225. Min Act: -0.1700
Data Index: 6820669 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.2539. Min Act: -0.1700
Data Index: 6198739 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.2382. Min Act: -0.1700
Data Index: 6198741 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.2067. Min Act: -0.1700
Data Index: 6198734 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.2067. Min Act: -0.1700
Data Index: 5209508 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.1753. Min Act: -0.1700
Data Index: 3298082 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.1595. Min Act: -0.1700
Data Index: 8481259 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.1753. Min Act: -0.1700
Data Index: 1990931 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.1595. Min Act: -0.1700
Data Index: 4395937 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.1595. Min Act: -0.1700
Data Index: 321337 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.1438. Min Act: -0.1700
Data Index: 210124 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.1438. Min Act: -0.1700
Data Index: 7165067 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.1281. Min Act: -0.1700
Data Index: 6285428 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.0965. Min Act: -0.1700
Data Index: 552667 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.0965. Min Act: -0.1700
Data Index: 6843041 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.0965. Min Act: -0.1700
Data Index: 6832705 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3638. Min Range: -3.3638
Max Act: 3.0965. Min Act: -0.1700
Data Index: 8528589 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19