Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4626 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2568. Min Range: -7.2568
Max Act: 7.2568. Min Act: -0.1700
Data Index: 556293 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2568. Min Range: -7.2568
Max Act: 7.0693. Min Act: -0.1700
Data Index: 1299554 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.9756. Min Act: -0.1700
Data Index: 3685383 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.9443. Min Act: -0.1700
Data Index: 2984600 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.8506. Min Act: -0.1700
Data Index: 3586429 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.7568. Min Act: -0.1700
Data Index: 6764046 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.7568. Min Act: -0.1700
Data Index: 1911820 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.6943. Min Act: -0.1700
Data Index: 5454581 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.7568. Min Act: -0.1700
Data Index: 2280373 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.6943. Min Act: -0.1700
Data Index: 3567205 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.7568. Min Act: -0.1700
Data Index: 6342491 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.6943. Min Act: -0.1700
Data Index: 8096362 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.6631. Min Act: -0.1700
Data Index: 2292508 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.6006. Min Act: -0.1700
Data Index: 2739253 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.6318. Min Act: -0.1700
Data Index: 3291910 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.6318. Min Act: -0.1700
Data Index: 7052150 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.6318. Min Act: -0.1700
Data Index: 3001876 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.6006. Min Act: -0.1700
Data Index: 2739267 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.6006. Min Act: -0.1700
Data Index: 811531 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2568. Min Range: -7.2568
Max Act: 6.5693. Min Act: -0.1700
Data Index: 7988267 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19