Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 836 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.5025. Min Act: -0.1700
Data Index: 3330287 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.3150. Min Act: -0.1700
Data Index: 2714939 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.3150. Min Act: -0.1700
Data Index: 3459415 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.3150. Min Act: -0.1700
Data Index: 7897086 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.2837. Min Act: -0.1700
Data Index: 4926485 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.2524. Min Act: -0.1700
Data Index: 5330143 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.2524. Min Act: -0.1700
Data Index: 6353044 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.2212. Min Act: -0.1700
Data Index: 1201883 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.2212. Min Act: -0.1700
Data Index: 3641618 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.1587. Min Act: -0.1700
Data Index: 6351705 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.1587. Min Act: -0.1700
Data Index: 2476701 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.1274. Min Act: -0.1700
Data Index: 6675981 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.1274. Min Act: -0.1700
Data Index: 6748648 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.0962. Min Act: -0.1700
Data Index: 3434745 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.0962. Min Act: -0.1700
Data Index: 4039810 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.0649. Min Act: -0.1700
Data Index: 319710 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.0649. Min Act: -0.1700
Data Index: 1898012 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.0649. Min Act: -0.1700
Data Index: 966888 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.0649. Min Act: -0.1700
Data Index: 858350 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5025. Min Range: -4.5025
Max Act: 4.0649. Min Act: -0.1700
Data Index: 4745884 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19