Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 317 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6792. Min Act: -0.1700
Data Index: 3587550 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6479. Min Act: -0.1700
Data Index: 8590076 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6167. Min Act: -0.1700
Data Index: 3505096 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6167. Min Act: -0.1700
Data Index: 6776701 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6479. Min Act: -0.1700
Data Index: 469943 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6167. Min Act: -0.1700
Data Index: 3494869 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6167. Min Act: -0.1700
Data Index: 863340 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6167. Min Act: -0.1700
Data Index: 3518181 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6167. Min Act: -0.1700
Data Index: 3537119 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6167. Min Act: -0.1700
Data Index: 1058557 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6167. Min Act: -0.1700
Data Index: 4291684 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6167. Min Act: -0.1700
Data Index: 5155488 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6167. Min Act: -0.1700
Data Index: 234181 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.6167. Min Act: -0.1700
Data Index: 2500286 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.5542. Min Act: -0.1700
Data Index: 5629472 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.5542. Min Act: -0.1700
Data Index: 3149527 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.5542. Min Act: -0.1700
Data Index: 4968290 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.5542. Min Act: -0.1700
Data Index: 473569 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.5542. Min Act: -0.1700
Data Index: 4037608 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6792. Min Range: -5.6792
Max Act: 5.5854. Min Act: -0.1700
Data Index: 916502 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19