Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4423 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.3351. Min Act: -0.1700
Data Index: 7020552 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.3037. Min Act: -0.1700
Data Index: 6558503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.3037. Min Act: -0.1700
Data Index: 30993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.3037. Min Act: -0.1700
Data Index: 2277189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2723. Min Act: -0.1700
Data Index: 6233907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2409. Min Act: -0.1700
Data Index: 1150914 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2409. Min Act: -0.1700
Data Index: 1071591 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2723. Min Act: -0.1700
Data Index: 2093451 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2723. Min Act: -0.1700
Data Index: 8801438 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2723. Min Act: -0.1700
Data Index: 5709440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2409. Min Act: -0.1700
Data Index: 4146298 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2409. Min Act: -0.1700
Data Index: 2746686 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2409. Min Act: -0.1700
Data Index: 4053678 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2409. Min Act: -0.1700
Data Index: 813647 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2409. Min Act: -0.1700
Data Index: 2929675 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2409. Min Act: -0.1700
Data Index: 4202900 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2409. Min Act: -0.1700
Data Index: 3970365 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2409. Min Act: -0.1700
Data Index: 440366 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2409. Min Act: -0.1700
Data Index: 4294411 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3351. Min Range: -3.3351
Max Act: 3.2409. Min Act: -0.1700
Data Index: 3939788 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19