Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1608 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.4222. Min Act: -0.1700
Data Index: 7093570 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.4222. Min Act: -0.1700
Data Index: 1373697 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.4222. Min Act: -0.1700
Data Index: 4508553 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.2660. Min Act: -0.1700
Data Index: 278804 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.1722. Min Act: -0.1700
Data Index: 6224554 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.1722. Min Act: -0.1700
Data Index: 3024144 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.2035. Min Act: -0.1700
Data Index: 3192447 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.1722. Min Act: -0.1700
Data Index: 3475059 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.1410. Min Act: -0.1700
Data Index: 6126549 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.0785. Min Act: -0.1700
Data Index: 2715611 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.0472. Min Act: -0.1700
Data Index: 1751504 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.0472. Min Act: -0.1700
Data Index: 2178859 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.0472. Min Act: -0.1700
Data Index: 5649321 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4222. Min Range: -7.4222
Max Act: 6.9847. Min Act: -0.1700
Data Index: 8170122 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.0160. Min Act: -0.1700
Data Index: 230379 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.0472. Min Act: -0.1700
Data Index: 7557882 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4222. Min Range: -7.4222
Max Act: 6.9847. Min Act: -0.1700
Data Index: 2397026 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.0160. Min Act: -0.1700
Data Index: 680713 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.0472. Min Act: -0.1700
Data Index: 5156213 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4222. Min Range: -7.4222
Max Act: 7.0160. Min Act: -0.1700
Data Index: 253070 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19