Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1040 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1477. Min Range: -6.1477
Max Act: 6.1477. Min Act: -0.1700
Data Index: 4330459 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.8977. Min Act: -0.1700
Data Index: 4882225 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.8664. Min Act: -0.1700
Data Index: 3483887 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.8664. Min Act: -0.1700
Data Index: 4245197 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.8039. Min Act: -0.1700
Data Index: 8092755 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.7727. Min Act: -0.1700
Data Index: 1582623 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.7414. Min Act: -0.1700
Data Index: 3040105 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.7414. Min Act: -0.1700
Data Index: 2495558 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.7414. Min Act: -0.1700
Data Index: 3496980 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.7414. Min Act: -0.1700
Data Index: 4728816 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.7102. Min Act: -0.1700
Data Index: 485297 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.6789. Min Act: -0.1700
Data Index: 1582617 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.6789. Min Act: -0.1700
Data Index: 2614820 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.6789. Min Act: -0.1700
Data Index: 8270120 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.6477. Min Act: -0.1700
Data Index: 7529076 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.6789. Min Act: -0.1700
Data Index: 790884 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.6164. Min Act: -0.1700
Data Index: 5529693 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.6164. Min Act: -0.1700
Data Index: 6460479 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.5852. Min Act: -0.1700
Data Index: 5792278 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1477. Min Range: -6.1477
Max Act: 5.5852. Min Act: -0.1700
Data Index: 7128442 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19