Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3238 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.3344. Min Act: -0.1700
Data Index: 2645111 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.2686. Min Act: -0.1700
Data Index: 2546638 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.2356. Min Act: -0.1700
Data Index: 7526372 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.2521. Min Act: -0.1700
Data Index: 770847 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.2521. Min Act: -0.1700
Data Index: 751179 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.2190. Min Act: -0.1700
Data Index: 8369214 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.2356. Min Act: -0.1700
Data Index: 4087137 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.2190. Min Act: -0.1700
Data Index: 6972072 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.2190. Min Act: -0.1700
Data Index: 1051836 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.2025. Min Act: -0.1700
Data Index: 2115308 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.2025. Min Act: -0.1700
Data Index: 4321731 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.2190. Min Act: -0.1700
Data Index: 2526666 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.1859. Min Act: -0.1700
Data Index: 6128836 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.1859. Min Act: -0.1700
Data Index: 4562179 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.1859. Min Act: -0.1700
Data Index: 3866722 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.2025. Min Act: -0.1700
Data Index: 6236903 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.1859. Min Act: -0.1700
Data Index: 671477 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.1859. Min Act: -0.1700
Data Index: 4762358 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.1692. Min Act: -0.1700
Data Index: 2829013 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3344. Min Range: -2.3344
Max Act: 2.1692. Min Act: -0.1700
Data Index: 2289670 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19