Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2827 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7413. Min Range: -6.7413
Max Act: 6.7413. Min Act: -0.1700
Data Index: 7716659 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7413. Min Range: -6.7413
Max Act: 6.6163. Min Act: -0.1700
Data Index: 5677033 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7413. Min Range: -6.7413
Max Act: 6.3663. Min Act: -0.1700
Data Index: 7826924 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7413. Min Range: -6.7413
Max Act: 6.3351. Min Act: -0.1700
Data Index: 4565056 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7413. Min Range: -6.7413
Max Act: 6.2726. Min Act: -0.1700
Data Index: 1936978 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7413. Min Range: -6.7413
Max Act: 6.2726. Min Act: -0.1700
Data Index: 859499 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7413. Min Range: -6.7413
Max Act: 6.2413. Min Act: -0.1700
Data Index: 2514528 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7413. Min Range: -6.7413
Max Act: 6.2413. Min Act: -0.1700
Data Index: 3306259 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7413. Min Range: -6.7413
Max Act: 6.2101. Min Act: -0.1700
Data Index: 7163735 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7413. Min Range: -6.7413
Max Act: 6.0851. Min Act: -0.1700
Data Index: 5582963 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7413. Min Range: -6.7413
Max Act: 5.9913. Min Act: -0.1700
Data Index: 6684832 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7413. Min Range: -6.7413
Max Act: 6.0226. Min Act: -0.1700
Data Index: 7414268 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7413. Min Range: -6.7413
Max Act: 6.0226. Min Act: -0.1700
Data Index: 2850168 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7413. Min Range: -6.7413
Max Act: 5.9288. Min Act: -0.1700
Data Index: 5567473 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7413. Min Range: -6.7413
Max Act: 5.9288. Min Act: -0.1700
Data Index: 6269692 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7413. Min Range: -6.7413
Max Act: 5.8976. Min Act: -0.1700
Data Index: 3181011 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7413. Min Range: -6.7413
Max Act: 5.8976. Min Act: -0.1700
Data Index: 3202799 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7413. Min Range: -6.7413
Max Act: 5.8663. Min Act: -0.1700
Data Index: 246628 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7413. Min Range: -6.7413
Max Act: 5.8351. Min Act: -0.1700
Data Index: 7986064 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7413. Min Range: -6.7413
Max Act: 5.8351. Min Act: -0.1700
Data Index: 300743 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19