Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.9573. Min Act: -0.1700
Data Index: 4498833 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.9063. Min Act: -0.1700
Data Index: 3944156 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.9063. Min Act: -0.1700
Data Index: 4889619 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.9063. Min Act: -0.1699
Data Index: 3141077 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.9063. Min Act: -0.1700
Data Index: 3218131 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8721. Min Act: -0.1700
Data Index: 2339788 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8892. Min Act: -0.1700
Data Index: 330368 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8721. Min Act: -0.1699
Data Index: 3588987 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8721. Min Act: -0.1700
Data Index: 7051445 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8721. Min Act: -0.1700
Data Index: 3934149 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8721. Min Act: -0.1700
Data Index: 1722701 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8721. Min Act: -0.1700
Data Index: 8590626 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8721. Min Act: -0.1700
Data Index: 2250376 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8721. Min Act: -0.1699
Data Index: 3277589 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8721. Min Act: -0.1700
Data Index: 4654087 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8721. Min Act: -0.1700
Data Index: 780914 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8550. Min Act: -0.1700
Data Index: 1858241 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8550. Min Act: -0.1699
Data Index: 2459768 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8550. Min Act: -0.1699
Data Index: 7341700 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9573. Min Range: -1.9573
Max Act: 1.8550. Min Act: -0.1700
Data Index: 615116 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19