Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 849 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0122. Min Range: -6.0122
Max Act: 6.0122. Min Act: -0.1700
Data Index: 8451839 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.9809. Min Act: -0.1700
Data Index: 7351620 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.8559. Min Act: -0.1700
Data Index: 4775412 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.7934. Min Act: -0.1700
Data Index: 7485582 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.7622. Min Act: -0.1700
Data Index: 2993944 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.6997. Min Act: -0.1700
Data Index: 8589063 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.6997. Min Act: -0.1700
Data Index: 5707405 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.6684. Min Act: -0.1700
Data Index: 1712279 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.6684. Min Act: -0.1700
Data Index: 5707406 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.6684. Min Act: -0.1700
Data Index: 1146337 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.6684. Min Act: -0.1700
Data Index: 1311132 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.6372. Min Act: -0.1700
Data Index: 6514349 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.5747. Min Act: -0.1700
Data Index: 8642982 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.5747. Min Act: -0.1700
Data Index: 3876235 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.5434. Min Act: -0.1700
Data Index: 1887483 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.5747. Min Act: -0.1700
Data Index: 253079 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.5434. Min Act: -0.1700
Data Index: 6416625 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.5434. Min Act: -0.1700
Data Index: 3448417 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.5122. Min Act: -0.1700
Data Index: 4992840 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0122. Min Range: -6.0122
Max Act: 5.5122. Min Act: -0.1700
Data Index: 1712291 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19