Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2528 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.5550. Min Act: -0.1700
Data Index: 5494661 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.5237. Min Act: -0.1700
Data Index: 328549 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.4925. Min Act: -0.1700
Data Index: 2138379 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.5237. Min Act: -0.1700
Data Index: 2328766 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.4300. Min Act: -0.1700
Data Index: 3404037 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.4300. Min Act: -0.1700
Data Index: 4075786 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.4300. Min Act: -0.1700
Data Index: 7860406 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3675. Min Act: -0.1700
Data Index: 2553092 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3362. Min Act: -0.1700
Data Index: 3215304 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3362. Min Act: -0.1700
Data Index: 3961686 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3362. Min Act: -0.1700
Data Index: 3629501 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3362. Min Act: -0.1700
Data Index: 6256262 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.2737. Min Act: -0.1700
Data Index: 247578 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3050. Min Act: -0.1700
Data Index: 7128855 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.2737. Min Act: -0.1700
Data Index: 7850160 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.3050. Min Act: -0.1700
Data Index: 3237321 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.2737. Min Act: -0.1700
Data Index: 7323280 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.2425. Min Act: -0.1700
Data Index: 6828266 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.2737. Min Act: -0.1700
Data Index: 1795569 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5550. Min Range: -4.5550
Max Act: 4.2425. Min Act: -0.1700
Data Index: 1436724 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19