Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1904 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.9422. Min Act: -0.1700
Data Index: 684244 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.9110. Min Act: -0.1700
Data Index: 450897 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.9110. Min Act: -0.1700
Data Index: 3329592 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.7860. Min Act: -0.1700
Data Index: 2150932 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.7235. Min Act: -0.1700
Data Index: 3968294 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.7235. Min Act: -0.1700
Data Index: 3968290 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6922. Min Act: -0.1700
Data Index: 2276334 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6922. Min Act: -0.1700
Data Index: 6516449 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6610. Min Act: -0.1700
Data Index: 4149015 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6610. Min Act: -0.1700
Data Index: 654086 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6610. Min Act: -0.1700
Data Index: 7737918 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6297. Min Act: -0.1700
Data Index: 921647 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6297. Min Act: -0.1700
Data Index: 1658356 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.5985. Min Act: -0.1700
Data Index: 6368789 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.5985. Min Act: -0.1700
Data Index: 258564 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.5985. Min Act: -0.1700
Data Index: 1299591 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.5985. Min Act: -0.1700
Data Index: 3831785 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.5985. Min Act: -0.1700
Data Index: 1806485 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.6297. Min Act: -0.1700
Data Index: 5921187 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9422. Min Range: -5.9422
Max Act: 5.5985. Min Act: -0.1700
Data Index: 5657376 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19