Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4083 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.1978. Min Act: -0.1700
Data Index: 1745573 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.1506. Min Act: -0.1700
Data Index: 7738266 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.1348. Min Act: -0.1700
Data Index: 7373634 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.1506. Min Act: -0.1700
Data Index: 4565221 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.1348. Min Act: -0.1700
Data Index: 462640 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.1348. Min Act: -0.1700
Data Index: 1934185 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.1348. Min Act: -0.1700
Data Index: 6042614 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.1033. Min Act: -0.1700
Data Index: 8810222 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.1033. Min Act: -0.1700
Data Index: 2250737 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.1033. Min Act: -0.1700
Data Index: 3211242 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.0718. Min Act: -0.1700
Data Index: 625496 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.0875. Min Act: -0.1700
Data Index: 1451443 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.0875. Min Act: -0.1700
Data Index: 6741817 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.0875. Min Act: -0.1700
Data Index: 836887 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.0560. Min Act: -0.1700
Data Index: 7006965 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.0560. Min Act: -0.1700
Data Index: 1349486 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.0560. Min Act: -0.1700
Data Index: 8481111 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.0560. Min Act: -0.1700
Data Index: 5150 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.0402. Min Act: -0.1700
Data Index: 6946979 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1978. Min Range: -3.1978
Max Act: 3.0402. Min Act: -0.1700
Data Index: 8791090 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19