Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3792 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.5710. Min Act: -0.1700
Data Index: 5524815 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.5710. Min Act: -0.1700
Data Index: 4293365 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.5241. Min Act: -0.1700
Data Index: 7763242 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.5084. Min Act: -0.1700
Data Index: 241243 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.5084. Min Act: -0.1700
Data Index: 3880004 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.4614. Min Act: -0.1700
Data Index: 3534892 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.4457. Min Act: -0.1700
Data Index: 5523612 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.4457. Min Act: -0.1700
Data Index: 948233 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.4457. Min Act: -0.1700
Data Index: 5697380 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.4457. Min Act: -0.1700
Data Index: 600629 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.4614. Min Act: -0.1700
Data Index: 4906336 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.4457. Min Act: -0.1700
Data Index: 6809738 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.4301. Min Act: -0.1700
Data Index: 2036876 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.4144. Min Act: -0.1700
Data Index: 744800 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.3987. Min Act: -0.1700
Data Index: 740422 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.3830. Min Act: -0.1700
Data Index: 4944552 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.3987. Min Act: -0.1700
Data Index: 4978240 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.3830. Min Act: -0.1700
Data Index: 4696019 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.3987. Min Act: -0.1700
Data Index: 293606 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5710. Min Range: -3.5710
Max Act: 3.3830. Min Act: -0.1700
Data Index: 7479121 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19