Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.5561. Min Act: -0.1700
Data Index: 8290943 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.4935. Min Act: -0.1700
Data Index: 8508915 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.4621. Min Act: -0.1700
Data Index: 1348871 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.4465. Min Act: -0.1700
Data Index: 8744609 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.4621. Min Act: -0.1700
Data Index: 4195969 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.4308. Min Act: -0.1700
Data Index: 775941 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.4465. Min Act: -0.1700
Data Index: 2045431 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.4465. Min Act: -0.1700
Data Index: 5327573 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.4151. Min Act: -0.1700
Data Index: 6457998 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.4151. Min Act: -0.1700
Data Index: 6594428 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.4308. Min Act: -0.1700
Data Index: 8642575 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.3681. Min Act: -0.1700
Data Index: 2212170 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.3681. Min Act: -0.1700
Data Index: 4562480 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.3681. Min Act: -0.1700
Data Index: 6213993 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.3681. Min Act: -0.1700
Data Index: 587460 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.3681. Min Act: -0.1700
Data Index: 4558663 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.3524. Min Act: -0.1700
Data Index: 2076154 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.3367. Min Act: -0.1700
Data Index: 2750379 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.3367. Min Act: -0.1700
Data Index: 3997718 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5561. Min Range: -3.5561
Max Act: 3.3210. Min Act: -0.1700
Data Index: 1183298 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19