Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3073 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.7482. Min Act: -0.1700
Data Index: 6621714 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.6232. Min Act: -0.1700
Data Index: 5740825 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.5920. Min Act: -0.1700
Data Index: 7270686 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.5607. Min Act: -0.1700
Data Index: 1270242 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.4982. Min Act: -0.1700
Data Index: 5754619 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.4357. Min Act: -0.1700
Data Index: 4702903 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.4357. Min Act: -0.1700
Data Index: 4045231 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.4045. Min Act: -0.1700
Data Index: 8085460 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.4045. Min Act: -0.1700
Data Index: 4804955 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.3732. Min Act: -0.1700
Data Index: 731538 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.3732. Min Act: -0.1700
Data Index: 777066 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.3420. Min Act: -0.1700
Data Index: 5568871 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.3420. Min Act: -0.1700
Data Index: 4180255 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.2795. Min Act: -0.1700
Data Index: 3121875 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.3107. Min Act: -0.1700
Data Index: 8419946 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.2795. Min Act: -0.1700
Data Index: 7540562 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.3107. Min Act: -0.1700
Data Index: 3063446 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.2482. Min Act: -0.1700
Data Index: 3755239 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.2795. Min Act: -0.1700
Data Index: 632277 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7482. Min Range: -5.7482
Max Act: 5.2795. Min Act: -0.1700
Data Index: 5841101 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19