Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2037. Min Range: -7.2037
Max Act: 7.2037. Min Act: -0.1700
Data Index: 791393 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2037. Min Range: -7.2037
Max Act: 7.2037. Min Act: -0.1700
Data Index: 6682853 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2037. Min Range: -7.2037
Max Act: 7.1100. Min Act: -0.1700
Data Index: 4899552 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2037. Min Range: -7.2037
Max Act: 7.0787. Min Act: -0.1700
Data Index: 639889 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2037. Min Range: -7.2037
Max Act: 7.0787. Min Act: -0.1700
Data Index: 6682854 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2037. Min Range: -7.2037
Max Act: 7.0475. Min Act: -0.1700
Data Index: 6626634 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2037. Min Range: -7.2037
Max Act: 7.0162. Min Act: -0.1700
Data Index: 4165126 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2037. Min Range: -7.2037
Max Act: 7.0162. Min Act: -0.1700
Data Index: 4931446 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2037. Min Range: -7.2037
Max Act: 6.9850. Min Act: -0.1700
Data Index: 74862 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2037. Min Range: -7.2037
Max Act: 6.9537. Min Act: -0.1700
Data Index: 8311782 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2037. Min Range: -7.2037
Max Act: 6.9225. Min Act: -0.1700
Data Index: 5338550 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2037. Min Range: -7.2037
Max Act: 6.8912. Min Act: -0.1700
Data Index: 8617205 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2037. Min Range: -7.2037
Max Act: 6.9225. Min Act: -0.1700
Data Index: 2952947 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2037. Min Range: -7.2037
Max Act: 6.9225. Min Act: -0.1700
Data Index: 2478663 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2037. Min Range: -7.2037
Max Act: 6.9225. Min Act: -0.1700
Data Index: 7634476 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2037. Min Range: -7.2037
Max Act: 6.9225. Min Act: -0.1700
Data Index: 3777621 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2037. Min Range: -7.2037
Max Act: 6.8600. Min Act: -0.1700
Data Index: 7725559 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2037. Min Range: -7.2037
Max Act: 6.8912. Min Act: -0.1700
Data Index: 5702845 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2037. Min Range: -7.2037
Max Act: 6.8600. Min Act: -0.1700
Data Index: 7575780 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2037. Min Range: -7.2037
Max Act: 6.8600. Min Act: -0.1700
Data Index: 2621398 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19