Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3972 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.8082. Min Act: -0.1700
Data Index: 1186314 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.4957. Min Act: -0.1700
Data Index: 6762666 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.4957. Min Act: -0.1700
Data Index: 5707101 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.4332. Min Act: -0.1700
Data Index: 1603496 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.4332. Min Act: -0.1700
Data Index: 333865 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.3082. Min Act: -0.1700
Data Index: 3084028 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.1832. Min Act: -0.1700
Data Index: 347440 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.1207. Min Act: -0.1700
Data Index: 650732 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.1207. Min Act: -0.1700
Data Index: 5992419 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.2457. Min Act: -0.1700
Data Index: 8364780 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.0582. Min Act: -0.1700
Data Index: 6134243 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.1207. Min Act: -0.1700
Data Index: 3602634 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.1207. Min Act: -0.1700
Data Index: 5505326 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8082. Min Range: -9.8082
Max Act: 8.9957. Min Act: -0.1700
Data Index: 8689979 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8082. Min Range: -9.8082
Max Act: 8.9957. Min Act: -0.1700
Data Index: 691386 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.0582. Min Act: -0.1700
Data Index: 601280 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8082. Min Range: -9.8082
Max Act: 8.9957. Min Act: -0.1700
Data Index: 2503913 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.0582. Min Act: -0.1700
Data Index: 7044370 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.0582. Min Act: -0.1700
Data Index: 2020680 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8082. Min Range: -9.8082
Max Act: 9.1207. Min Act: -0.1700
Data Index: 215436 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19