Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.9549. Min Act: -0.1700
Data Index: 1880473 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.7049. Min Act: -0.1700
Data Index: 3270051 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.7362. Min Act: -0.1700
Data Index: 3046719 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.7049. Min Act: -0.1700
Data Index: 8033555 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.6737. Min Act: -0.1700
Data Index: 1880472 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.6424. Min Act: -0.1700
Data Index: 3805802 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.5487. Min Act: -0.1700
Data Index: 8033556 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.5174. Min Act: -0.1700
Data Index: 3234620 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.5174. Min Act: -0.1700
Data Index: 4943859 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.4237. Min Act: -0.1700
Data Index: 3067536 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.4549. Min Act: -0.1700
Data Index: 7868701 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.4549. Min Act: -0.1700
Data Index: 4203482 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.4237. Min Act: -0.1700
Data Index: 2306821 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.4237. Min Act: -0.1700
Data Index: 3664306 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.4237. Min Act: -0.1700
Data Index: 3664310 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.4237. Min Act: -0.1700
Data Index: 5313188 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.4237. Min Act: -0.1700
Data Index: 1916032 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.4237. Min Act: -0.1700
Data Index: 4186375 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.3924. Min Act: -0.1700
Data Index: 7849579 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9549. Min Range: -7.9549
Max Act: 7.3924. Min Act: -0.1700
Data Index: 3466182 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19