Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1364. Min Range: -7.1364
Max Act: 7.1364. Min Act: -0.1700
Data Index: 4958980 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1364. Min Range: -7.1364
Max Act: 7.0114. Min Act: -0.1700
Data Index: 3098826 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.9177. Min Act: -0.1700
Data Index: 5464649 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.9177. Min Act: -0.1700
Data Index: 3742854 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.8864. Min Act: -0.1700
Data Index: 1909572 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.6677. Min Act: -0.1700
Data Index: 1032198 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.6989. Min Act: -0.1700
Data Index: 3260924 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.6364. Min Act: -0.1700
Data Index: 3879974 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.6364. Min Act: -0.1700
Data Index: 7162649 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.6052. Min Act: -0.1700
Data Index: 1588837 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.6052. Min Act: -0.1700
Data Index: 2317056 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.5739. Min Act: -0.1700
Data Index: 8221204 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.5427. Min Act: -0.1700
Data Index: 2974370 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.5739. Min Act: -0.1700
Data Index: 8375177 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.5114. Min Act: -0.1700
Data Index: 2856413 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.5114. Min Act: -0.1700
Data Index: 3836429 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.5114. Min Act: -0.1700
Data Index: 7832366 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.4802. Min Act: -0.1700
Data Index: 1288636 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.4489. Min Act: -0.1700
Data Index: 8614799 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1364. Min Range: -7.1364
Max Act: 6.4802. Min Act: -0.1700
Data Index: 5361962 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19