Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0110. Min Range: -7.0110
Max Act: 7.0110. Min Act: -0.1700
Data Index: 4294419 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.4173. Min Act: -0.1700
Data Index: 373413 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.3860. Min Act: -0.1700
Data Index: 1896400 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.3548. Min Act: -0.1700
Data Index: 1992486 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.3235. Min Act: -0.1700
Data Index: 273996 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.2923. Min Act: -0.1700
Data Index: 3550002 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.2610. Min Act: -0.1700
Data Index: 8255606 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.2923. Min Act: -0.1700
Data Index: 6738625 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.2298. Min Act: -0.1700
Data Index: 1712050 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.2298. Min Act: -0.1700
Data Index: 2003388 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.1673. Min Act: -0.1700
Data Index: 65670 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.1985. Min Act: -0.1700
Data Index: 8628156 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.1985. Min Act: -0.1700
Data Index: 7651906 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.1985. Min Act: -0.1700
Data Index: 1580700 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.1360. Min Act: -0.1700
Data Index: 7954179 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.1673. Min Act: -0.1700
Data Index: 437696 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.1360. Min Act: -0.1700
Data Index: 790316 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.1360. Min Act: -0.1700
Data Index: 3815419 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.1360. Min Act: -0.1700
Data Index: 8123828 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0110. Min Range: -7.0110
Max Act: 6.1360. Min Act: -0.1700
Data Index: 2723424 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19