Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4102 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.4485. Min Act: -0.1700
Data Index: 910050 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.4485. Min Act: -0.1700
Data Index: 5161334 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.4173. Min Act: -0.1700
Data Index: 4352487 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.3860. Min Act: -0.1700
Data Index: 7424599 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.3548. Min Act: -0.1700
Data Index: 2919223 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.1985. Min Act: -0.1700
Data Index: 2195700 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.1985. Min Act: -0.1700
Data Index: 8239027 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.1673. Min Act: -0.1700
Data Index: 666682 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.1360. Min Act: -0.1700
Data Index: 339125 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.1673. Min Act: -0.1700
Data Index: 7215816 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.1048. Min Act: -0.1700
Data Index: 2599123 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.1048. Min Act: -0.1700
Data Index: 5104138 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.1048. Min Act: -0.1700
Data Index: 7023617 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.0735. Min Act: -0.1700
Data Index: 1680150 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.1048. Min Act: -0.1700
Data Index: 8582970 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.0735. Min Act: -0.1700
Data Index: 2486685 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.0735. Min Act: -0.1700
Data Index: 488590 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.0110. Min Act: -0.1700
Data Index: 4270810 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.0423. Min Act: -0.1700
Data Index: 6751110 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4485. Min Range: -5.4485
Max Act: 5.0423. Min Act: -0.1700
Data Index: 6535238 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19