Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5386 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1556. Min Range: -5.1556
Max Act: 5.1556. Min Act: -0.1700
Data Index: 3360982 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1556. Min Range: -5.1556
Max Act: 5.0931. Min Act: -0.1700
Data Index: 5220151 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.9056. Min Act: -0.1700
Data Index: 3286999 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.8431. Min Act: -0.1700
Data Index: 793206 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.8431. Min Act: -0.1700
Data Index: 4914873 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.7493. Min Act: -0.1700
Data Index: 7252009 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.7181. Min Act: -0.1700
Data Index: 5030768 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.7181. Min Act: -0.1700
Data Index: 8409450 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.7181. Min Act: -0.1700
Data Index: 1110768 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.6556. Min Act: -0.1700
Data Index: 4109013 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.6868. Min Act: -0.1700
Data Index: 6826468 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.6556. Min Act: -0.1700
Data Index: 2520567 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.6243. Min Act: -0.1700
Data Index: 7494920 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.6556. Min Act: -0.1700
Data Index: 2701747 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.6556. Min Act: -0.1700
Data Index: 4480684 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.6243. Min Act: -0.1700
Data Index: 2793212 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.6243. Min Act: -0.1700
Data Index: 2647250 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.6243. Min Act: -0.1700
Data Index: 2363537 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.6556. Min Act: -0.1700
Data Index: 5501843 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1556. Min Range: -5.1556
Max Act: 4.5931. Min Act: -0.1700
Data Index: 2560563 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19