Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3129 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.2915. Min Act: -0.1700
Data Index: 7589061 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.2915. Min Act: -0.1700
Data Index: 5775810 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.2602. Min Act: -0.1700
Data Index: 1899641 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.2290. Min Act: -0.1700
Data Index: 2225213 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.1977. Min Act: -0.1700
Data Index: 4149367 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.1665. Min Act: -0.1700
Data Index: 2592551 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.1977. Min Act: -0.1700
Data Index: 7862028 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.1665. Min Act: -0.1700
Data Index: 2913776 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.1040. Min Act: -0.1700
Data Index: 5350296 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.1665. Min Act: -0.1700
Data Index: 4717679 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.1040. Min Act: -0.1700
Data Index: 8799990 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.1352. Min Act: -0.1700
Data Index: 4359131 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.1040. Min Act: -0.1700
Data Index: 7329364 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.0727. Min Act: -0.1700
Data Index: 4655396 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.0727. Min Act: -0.1700
Data Index: 6180097 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.0102. Min Act: -0.1700
Data Index: 6856202 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.0102. Min Act: -0.1700
Data Index: 7084909 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2915. Min Range: -5.2915
Max Act: 5.0415. Min Act: -0.1700
Data Index: 1078141 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2915. Min Range: -5.2915
Max Act: 4.9790. Min Act: -0.1700
Data Index: 5641652 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2915. Min Range: -5.2915
Max Act: 4.9477. Min Act: -0.1700
Data Index: 2706283 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19