Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2443 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.6750. Min Act: -0.1700
Data Index: 5274280 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.5464. Min Act: -0.1700
Data Index: 1548336 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.5302. Min Act: -0.1700
Data Index: 953450 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.5464. Min Act: -0.1700
Data Index: 7023279 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4978. Min Act: -0.1700
Data Index: 1751298 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4816. Min Act: -0.1700
Data Index: 2537179 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4816. Min Act: -0.1700
Data Index: 7940056 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4329. Min Act: -0.1700
Data Index: 932512 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4329. Min Act: -0.1700
Data Index: 5389472 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4166. Min Act: -0.1700
Data Index: 8244608 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4329. Min Act: -0.1700
Data Index: 8403050 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4329. Min Act: -0.1700
Data Index: 4718624 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4329. Min Act: -0.1700
Data Index: 2055632 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4166. Min Act: -0.1700
Data Index: 2600535 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4003. Min Act: -0.1700
Data Index: 4799363 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4003. Min Act: -0.1700
Data Index: 36768 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4166. Min Act: -0.1700
Data Index: 2524002 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4003. Min Act: -0.1700
Data Index: 7725760 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.4003. Min Act: -0.1700
Data Index: 4099439 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6750. Min Range: -2.6750
Max Act: 2.3839. Min Act: -0.1700
Data Index: 5693570 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19