Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1047 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4038. Min Range: -5.4038
Max Act: 5.4038. Min Act: -0.1700
Data Index: 3657889 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4038. Min Range: -5.4038
Max Act: 5.3413. Min Act: -0.1700
Data Index: 7171877 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4038. Min Range: -5.4038
Max Act: 5.3101. Min Act: -0.1700
Data Index: 963947 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4038. Min Range: -5.4038
Max Act: 5.2163. Min Act: -0.1700
Data Index: 7903921 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4038. Min Range: -5.4038
Max Act: 5.0601. Min Act: -0.1700
Data Index: 1330499 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4038. Min Range: -5.4038
Max Act: 5.0601. Min Act: -0.1700
Data Index: 583699 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4038. Min Range: -5.4038
Max Act: 5.0288. Min Act: -0.1700
Data Index: 7231083 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.9976. Min Act: -0.1700
Data Index: 4689293 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.9976. Min Act: -0.1700
Data Index: 3365038 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.9038. Min Act: -0.1700
Data Index: 240892 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.9351. Min Act: -0.1700
Data Index: 2843970 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.9351. Min Act: -0.1700
Data Index: 5845397 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.9038. Min Act: -0.1700
Data Index: 7714110 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.9038. Min Act: -0.1700
Data Index: 7377724 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.9038. Min Act: -0.1700
Data Index: 642876 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.8726. Min Act: -0.1700
Data Index: 2126396 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.8726. Min Act: -0.1700
Data Index: 1053024 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.8726. Min Act: -0.1700
Data Index: 502084 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.8413. Min Act: -0.1700
Data Index: 5370136 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4038. Min Range: -5.4038
Max Act: 4.8413. Min Act: -0.1700
Data Index: 4809946 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19