Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4912 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.2381. Min Act: -0.1700
Data Index: 3307408 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.2069. Min Act: -0.1700
Data Index: 289830 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.2069. Min Act: -0.1700
Data Index: 4748269 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.1444. Min Act: -0.1700
Data Index: 3927784 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.1131. Min Act: -0.1700
Data Index: 5939258 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.1444. Min Act: -0.1700
Data Index: 4189582 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.1444. Min Act: -0.1700
Data Index: 8424683 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.1131. Min Act: -0.1700
Data Index: 7246906 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.1131. Min Act: -0.1700
Data Index: 8693079 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.0819. Min Act: -0.1700
Data Index: 820920 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.0506. Min Act: -0.1700
Data Index: 1059102 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.0506. Min Act: -0.1700
Data Index: 3161182 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.0506. Min Act: -0.1700
Data Index: 6958036 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.0506. Min Act: -0.1700
Data Index: 8142314 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.0506. Min Act: -0.1700
Data Index: 2436879 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.0506. Min Act: -0.1700
Data Index: 1059099 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.0194. Min Act: -0.1700
Data Index: 6974087 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.0194. Min Act: -0.1700
Data Index: 3307409 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.0194. Min Act: -0.1700
Data Index: 5023168 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2381. Min Range: -5.2381
Max Act: 5.0194. Min Act: -0.1700
Data Index: 1059100 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19