Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4880 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.2850. Min Act: -0.1700
Data Index: 4640562 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.2225. Min Act: -0.1700
Data Index: 5694258 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.1600. Min Act: -0.1700
Data Index: 8350872 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.1287. Min Act: -0.1700
Data Index: 1860634 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.1287. Min Act: -0.1700
Data Index: 8478103 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.1287. Min Act: -0.1700
Data Index: 8516907 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.1287. Min Act: -0.1700
Data Index: 6022172 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0975. Min Act: -0.1700
Data Index: 3183829 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0975. Min Act: -0.1700
Data Index: 1479676 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0975. Min Act: -0.1700
Data Index: 8200030 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0975. Min Act: -0.1700
Data Index: 2938475 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0662. Min Act: -0.1700
Data Index: 8656745 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0662. Min Act: -0.1700
Data Index: 3786085 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0350. Min Act: -0.1700
Data Index: 1180468 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0350. Min Act: -0.1700
Data Index: 8565491 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0350. Min Act: -0.1700
Data Index: 820588 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0350. Min Act: -0.1700
Data Index: 8167319 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0350. Min Act: -0.1700
Data Index: 7225116 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0350. Min Act: -0.1700
Data Index: 4990242 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2850. Min Range: -7.2850
Max Act: 7.0037. Min Act: -0.1700
Data Index: 2103898 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19