Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5970 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7254. Min Range: -5.7254
Max Act: 5.7254. Min Act: -0.1700
Data Index: 4598435 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7254. Min Range: -5.7254
Max Act: 5.3817. Min Act: -0.1700
Data Index: 3239635 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7254. Min Range: -5.7254
Max Act: 5.1629. Min Act: -0.1700
Data Index: 1448928 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7254. Min Range: -5.7254
Max Act: 5.1004. Min Act: -0.1700
Data Index: 1209912 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7254. Min Range: -5.7254
Max Act: 5.0692. Min Act: -0.1700
Data Index: 1461539 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7254. Min Range: -5.7254
Max Act: 5.0067. Min Act: -0.1700
Data Index: 5723615 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7254. Min Range: -5.7254
Max Act: 5.0067. Min Act: -0.1700
Data Index: 1375835 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.9754. Min Act: -0.1700
Data Index: 3661943 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.9442. Min Act: -0.1700
Data Index: 2194258 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.9442. Min Act: -0.1700
Data Index: 1150006 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.9129. Min Act: -0.1700
Data Index: 6499012 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.9129. Min Act: -0.1700
Data Index: 4387251 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.8817. Min Act: -0.1700
Data Index: 1259015 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.8817. Min Act: -0.1700
Data Index: 1600395 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.8192. Min Act: -0.1700
Data Index: 3587866 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.8504. Min Act: -0.1700
Data Index: 2177311 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.8192. Min Act: -0.1700
Data Index: 2026797 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.8192. Min Act: -0.1700
Data Index: 1494821 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.8192. Min Act: -0.1700
Data Index: 4111278 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7254. Min Range: -5.7254
Max Act: 4.8192. Min Act: -0.1700
Data Index: 5558361 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19