Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2777 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.4600. Min Act: -0.1700
Data Index: 1290305 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3662. Min Act: -0.1700
Data Index: 6763475 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3350. Min Act: -0.1700
Data Index: 7195966 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3662. Min Act: -0.1700
Data Index: 5569229 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3350. Min Act: -0.1700
Data Index: 3308812 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3037. Min Act: -0.1700
Data Index: 5552241 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3037. Min Act: -0.1700
Data Index: 7290821 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3350. Min Act: -0.1700
Data Index: 3397266 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3037. Min Act: -0.1700
Data Index: 1067173 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3037. Min Act: -0.1700
Data Index: 5871190 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.2725. Min Act: -0.1700
Data Index: 1665676 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3350. Min Act: -0.1700
Data Index: 7428295 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3037. Min Act: -0.1700
Data Index: 7335363 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3037. Min Act: -0.1700
Data Index: 7197683 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.3037. Min Act: -0.1700
Data Index: 6174754 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.2725. Min Act: -0.1700
Data Index: 5909234 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.2725. Min Act: -0.1700
Data Index: 331846 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.2725. Min Act: -0.1700
Data Index: 2461309 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.2725. Min Act: -0.1700
Data Index: 3775072 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4600. Min Range: -4.4600
Max Act: 4.2725. Min Act: -0.1700
Data Index: 3814034 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19