Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 984 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.8861. Min Act: -0.1700
Data Index: 7737933 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.5111. Min Act: -0.1700
Data Index: 8189156 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.5111. Min Act: -0.1700
Data Index: 3480766 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.3861. Min Act: -0.1700
Data Index: 7654416 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.4486. Min Act: -0.1700
Data Index: 1416402 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.3548. Min Act: -0.1700
Data Index: 555944 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.3861. Min Act: -0.1700
Data Index: 7651840 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.2923. Min Act: -0.1700
Data Index: 6761315 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.3236. Min Act: -0.1700
Data Index: 319559 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.2923. Min Act: -0.1700
Data Index: 4551263 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.2298. Min Act: -0.1700
Data Index: 7732513 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.2923. Min Act: -0.1700
Data Index: 4612734 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.2298. Min Act: -0.1700
Data Index: 4432654 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.1986. Min Act: -0.1700
Data Index: 1417671 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.1986. Min Act: -0.1700
Data Index: 3385778 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.1986. Min Act: -0.1700
Data Index: 5895111 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.1986. Min Act: -0.1700
Data Index: 2426627 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.1986. Min Act: -0.1700
Data Index: 2136383 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.2611. Min Act: -0.1700
Data Index: 8025708 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8861. Min Range: -6.8861
Max Act: 6.1673. Min Act: -0.1700
Data Index: 5216274 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19