Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4640 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.2899. Min Act: -0.1700
Data Index: 2986453 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2899. Min Range: -4.2899
Max Act: 4.0086. Min Act: -0.1700
Data Index: 5851958 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.8210. Min Act: -0.1700
Data Index: 7174207 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.8210. Min Act: -0.1700
Data Index: 705391 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.7741. Min Act: -0.1700
Data Index: 4129765 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.7584. Min Act: -0.1700
Data Index: 2837915 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.6802. Min Act: -0.1700
Data Index: 3890608 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.6176. Min Act: -0.1700
Data Index: 8000003 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.6020. Min Act: -0.1700
Data Index: 3297302 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.5863. Min Act: -0.1700
Data Index: 1361761 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.5394. Min Act: -0.1700
Data Index: 1673583 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.5550. Min Act: -0.1700
Data Index: 8115978 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.5394. Min Act: -0.1700
Data Index: 3030722 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.5237. Min Act: -0.1700
Data Index: 7226380 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.5237. Min Act: -0.1700
Data Index: 163934 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.4924. Min Act: -0.1700
Data Index: 2759705 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.5080. Min Act: -0.1700
Data Index: 6512020 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.5080. Min Act: -0.1700
Data Index: 4839230 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.4924. Min Act: -0.1700
Data Index: 2438548 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2899. Min Range: -4.2899
Max Act: 3.4767. Min Act: -0.1700
Data Index: 8408471 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19