Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1474 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.2972. Min Range: -9.2972
Max Act: 9.2972. Min Act: -0.1700
Data Index: 7250921 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.9847. Min Act: -0.1700
Data Index: 6226276 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.8597. Min Act: -0.1700
Data Index: 7682583 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.9222. Min Act: -0.1617
Data Index: 523278 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.8597. Min Act: -0.1700
Data Index: 7099533 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.6722. Min Act: -0.1696
Data Index: 1575217 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.5472. Min Act: -0.1700
Data Index: 2885260 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.5472. Min Act: -0.1700
Data Index: 2168418 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.5472. Min Act: -0.1700
Data Index: 636983 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.4222. Min Act: -0.1700
Data Index: 2367589 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.3597. Min Act: -0.1698
Data Index: 768479 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.3597. Min Act: -0.1700
Data Index: 6991846 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.4222. Min Act: -0.1700
Data Index: 787417 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.3597. Min Act: -0.1668
Data Index: 5467855 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.3597. Min Act: -0.1698
Data Index: 5675933 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.3597. Min Act: -0.1700
Data Index: 7110718 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.4222. Min Act: -0.1700
Data Index: 2863891 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.2972. Min Act: -0.1700
Data Index: 2778352 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.3597. Min Act: -0.1700
Data Index: 2317568 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2972. Min Range: -9.2972
Max Act: 8.2972. Min Act: -0.1700
Data Index: 2072058 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19