Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1553 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0257. Min Range: -5.0257
Max Act: 5.0257. Min Act: -0.1700
Data Index: 7277107 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.8070. Min Act: -0.1700
Data Index: 6474902 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.7132. Min Act: -0.1700
Data Index: 5287866 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.7132. Min Act: -0.1700
Data Index: 5239037 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.7132. Min Act: -0.1700
Data Index: 6471231 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.6820. Min Act: -0.1700
Data Index: 6474901 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.6507. Min Act: -0.1700
Data Index: 7567976 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.6195. Min Act: -0.1700
Data Index: 5287865 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.6195. Min Act: -0.1700
Data Index: 2269581 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.5882. Min Act: -0.1700
Data Index: 2253996 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.5570. Min Act: -0.1700
Data Index: 6573524 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.5570. Min Act: -0.1700
Data Index: 3808012 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.5570. Min Act: -0.1700
Data Index: 6577007 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.5570. Min Act: -0.1700
Data Index: 1644592 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.5257. Min Act: -0.1700
Data Index: 2705722 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.5257. Min Act: -0.1700
Data Index: 5911742 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.5257. Min Act: -0.1700
Data Index: 8408722 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.5257. Min Act: -0.1700
Data Index: 1695672 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.5257. Min Act: -0.1700
Data Index: 6264023 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0257. Min Range: -5.0257
Max Act: 4.4945. Min Act: -0.1700
Data Index: 7530002 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19