Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1613 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.7290. Min Act: -0.1700
Data Index: 6848421 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.4477. Min Act: -0.1700
Data Index: 7964385 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.4165. Min Act: -0.1700
Data Index: 4946230 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.3852. Min Act: -0.1700
Data Index: 2115815 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.3227. Min Act: -0.1700
Data Index: 1134012 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.3227. Min Act: -0.1700
Data Index: 4975243 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.2915. Min Act: -0.1700
Data Index: 1690667 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.2602. Min Act: -0.1700
Data Index: 5249581 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.1977. Min Act: -0.1700
Data Index: 4754617 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.1977. Min Act: -0.1700
Data Index: 5440902 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.1665. Min Act: -0.1700
Data Index: 629847 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.1665. Min Act: -0.1700
Data Index: 7650127 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.1665. Min Act: -0.1700
Data Index: 7419395 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.1665. Min Act: -0.1700
Data Index: 8744608 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.1352. Min Act: -0.1700
Data Index: 7761085 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.1352. Min Act: -0.1700
Data Index: 1118124 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.1352. Min Act: -0.1700
Data Index: 8702022 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.1352. Min Act: -0.1700
Data Index: 661175 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.1352. Min Act: -0.1700
Data Index: 183014 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7290. Min Range: -5.7290
Max Act: 5.1040. Min Act: -0.1700
Data Index: 7186617 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19