Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3513 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.4319. Min Act: -0.1700
Data Index: 5264740 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.4006. Min Act: -0.1700
Data Index: 2177856 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.4006. Min Act: -0.1700
Data Index: 3015947 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3694. Min Act: -0.1700
Data Index: 955581 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3381. Min Act: -0.1700
Data Index: 8710914 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3381. Min Act: -0.1700
Data Index: 5551287 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3694. Min Act: -0.1700
Data Index: 6371428 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3694. Min Act: -0.1700
Data Index: 3967127 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3381. Min Act: -0.1700
Data Index: 2439334 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3694. Min Act: -0.1700
Data Index: 7880290 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3381. Min Act: -0.1700
Data Index: 1247415 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3069. Min Act: -0.1700
Data Index: 2302808 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.2756. Min Act: -0.1700
Data Index: 3219737 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3069. Min Act: -0.1700
Data Index: 660575 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.2756. Min Act: -0.1700
Data Index: 4577403 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.2756. Min Act: -0.1700
Data Index: 2923031 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.2444. Min Act: -0.1700
Data Index: 464334 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.2756. Min Act: -0.1700
Data Index: 8115291 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.2756. Min Act: -0.1700
Data Index: 2237700 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3069. Min Act: -0.1700
Data Index: 5511487 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19