Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1670 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.6225. Min Act: -0.1700
Data Index: 1224476 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.5600. Min Act: -0.1700
Data Index: 2601884 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.5600. Min Act: -0.1700
Data Index: 2333556 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.4662. Min Act: -0.1700
Data Index: 2874710 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.4662. Min Act: -0.1700
Data Index: 1562946 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.4350. Min Act: -0.1700
Data Index: 3120507 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.4037. Min Act: -0.1700
Data Index: 2360103 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3725. Min Act: -0.1700
Data Index: 4655556 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3725. Min Act: -0.1700
Data Index: 6787628 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3725. Min Act: -0.1700
Data Index: 7920062 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3725. Min Act: -0.1700
Data Index: 3074372 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3725. Min Act: -0.1700
Data Index: 5956438 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3412. Min Act: -0.1700
Data Index: 8769885 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3412. Min Act: -0.1700
Data Index: 4092400 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3100. Min Act: -0.1700
Data Index: 4036111 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3100. Min Act: -0.1700
Data Index: 4010511 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3100. Min Act: -0.1700
Data Index: 361805 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3412. Min Act: -0.1700
Data Index: 413170 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3725. Min Act: -0.1700
Data Index: 1758860 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6225. Min Range: -5.6225
Max Act: 5.3412. Min Act: -0.1700
Data Index: 5025246 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19