Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 959 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.3923. Min Act: -0.1700
Data Index: 7245432 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.2986. Min Act: -0.1700
Data Index: 1863307 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.2673. Min Act: -0.1700
Data Index: 149053 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.2361. Min Act: -0.1700
Data Index: 8805826 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.2048. Min Act: -0.1700
Data Index: 1922937 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.2361. Min Act: -0.1700
Data Index: 5977120 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.2673. Min Act: -0.1700
Data Index: 3286189 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.2048. Min Act: -0.1700
Data Index: 698870 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.2048. Min Act: -0.1700
Data Index: 3617599 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.1736. Min Act: -0.1700
Data Index: 2357784 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.1736. Min Act: -0.1700
Data Index: 1660770 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.1423. Min Act: -0.1700
Data Index: 5969819 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.1736. Min Act: -0.1700
Data Index: 5947965 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.1111. Min Act: -0.1700
Data Index: 3124335 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.0798. Min Act: -0.1700
Data Index: 7454466 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.0798. Min Act: -0.1700
Data Index: 6124856 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.0486. Min Act: -0.1700
Data Index: 5255467 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.0486. Min Act: -0.1700
Data Index: 5025772 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.0173. Min Act: -0.1700
Data Index: 5680106 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3923. Min Range: -5.3923
Max Act: 5.0173. Min Act: -0.1700
Data Index: 4453900 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19