Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4549 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.4563. Min Act: -0.1700
Data Index: 5505724 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.4251. Min Act: -0.1700
Data Index: 607990 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.4251. Min Act: -0.1700
Data Index: 4085065 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.4251. Min Act: -0.1700
Data Index: 4163953 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3938. Min Act: -0.1700
Data Index: 3986267 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3938. Min Act: -0.1700
Data Index: 545337 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3626. Min Act: -0.1700
Data Index: 3207034 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3313. Min Act: -0.1700
Data Index: 5314206 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3626. Min Act: -0.1700
Data Index: 3642639 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3626. Min Act: -0.1700
Data Index: 6554790 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3626. Min Act: -0.1700
Data Index: 1946725 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3626. Min Act: -0.1700
Data Index: 1678345 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3313. Min Act: -0.1700
Data Index: 8779433 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3313. Min Act: -0.1700
Data Index: 2908029 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3313. Min Act: -0.1700
Data Index: 1516000 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3001. Min Act: -0.1700
Data Index: 4165482 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3001. Min Act: -0.1700
Data Index: 3364981 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3001. Min Act: -0.1700
Data Index: 6788461 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.2688. Min Act: -0.1700
Data Index: 3954162 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4563. Min Range: -4.4563
Max Act: 4.3001. Min Act: -0.1700
Data Index: 1408048 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19