Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4363 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.8925. Min Act: -0.1700
Data Index: 2539426 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.8300. Min Act: -0.1700
Data Index: 2739590 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.5800. Min Act: -0.1700
Data Index: 2573258 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.5800. Min Act: -0.1700
Data Index: 3816907 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.5175. Min Act: -0.1700
Data Index: 6852887 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.5175. Min Act: -0.1700
Data Index: 141825 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.4550. Min Act: -0.1700
Data Index: 6220200 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.4550. Min Act: -0.1700
Data Index: 8170236 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.4550. Min Act: -0.1700
Data Index: 2800141 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.4550. Min Act: -0.1700
Data Index: 7026614 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.3300. Min Act: -0.1700
Data Index: 31470 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.3300. Min Act: -0.1700
Data Index: 7217565 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.2675. Min Act: -0.1700
Data Index: 4215969 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.2675. Min Act: -0.1700
Data Index: 1346751 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.2675. Min Act: -0.1700
Data Index: 1047203 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.2675. Min Act: -0.1700
Data Index: 5410289 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.2675. Min Act: -0.1700
Data Index: 1023029 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.3300. Min Act: -0.1700
Data Index: 485858 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.1425. Min Act: -0.1700
Data Index: 6803800 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8925. Min Range: -8.8925
Max Act: 8.1425. Min Act: -0.1700
Data Index: 1728100 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19