Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2058 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.8707. Min Act: -0.1700
Data Index: 532500 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.8394. Min Act: -0.1700
Data Index: 3119135 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.7457. Min Act: -0.1700
Data Index: 4816783 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.6832. Min Act: -0.1700
Data Index: 4456632 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.6832. Min Act: -0.1700
Data Index: 2882984 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.6519. Min Act: -0.1700
Data Index: 6368751 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.6519. Min Act: -0.1700
Data Index: 3098893 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.5894. Min Act: -0.1700
Data Index: 5208574 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.5894. Min Act: -0.1700
Data Index: 5574293 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.5269. Min Act: -0.1700
Data Index: 7771338 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.4644. Min Act: -0.1700
Data Index: 7122560 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.4644. Min Act: -0.1700
Data Index: 7334055 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.4957. Min Act: -0.1700
Data Index: 7532905 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.4957. Min Act: -0.1700
Data Index: 4903657 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.4332. Min Act: -0.1700
Data Index: 5878321 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.4019. Min Act: -0.1700
Data Index: 5893518 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.4019. Min Act: -0.1700
Data Index: 3323817 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.3394. Min Act: -0.1700
Data Index: 5026787 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.3082. Min Act: -0.1700
Data Index: 3935498 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8707. Min Range: -7.8707
Max Act: 7.3394. Min Act: -0.1700
Data Index: 2739278 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19