Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2831 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.4971. Min Act: -0.1700
Data Index: 2847452 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.4659. Min Act: -0.1700
Data Index: 6303625 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.4346. Min Act: -0.1700
Data Index: 8113280 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.3409. Min Act: -0.1700
Data Index: 6244925 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.2471. Min Act: -0.1700
Data Index: 4016025 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.2471. Min Act: -0.1700
Data Index: 2845739 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.2471. Min Act: -0.1700
Data Index: 6890394 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.2159. Min Act: -0.1700
Data Index: 5881986 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.2471. Min Act: -0.1700
Data Index: 1694909 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.2159. Min Act: -0.1700
Data Index: 2619413 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.1846. Min Act: -0.1700
Data Index: 3473285 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.1846. Min Act: -0.1700
Data Index: 1694908 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.1846. Min Act: -0.1700
Data Index: 3098663 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.1534. Min Act: -0.1700
Data Index: 42672 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.1534. Min Act: -0.1700
Data Index: 8634006 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.0908. Min Act: -0.1700
Data Index: 5336772 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.0908. Min Act: -0.1700
Data Index: 5918610 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.1221. Min Act: -0.1700
Data Index: 799036 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.1221. Min Act: -0.1700
Data Index: 532120 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4971. Min Range: -4.4971
Max Act: 4.0908. Min Act: -0.1700
Data Index: 4300433 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19