Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5697 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.9742. Min Act: -0.1700
Data Index: 3969663 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.8804. Min Act: -0.1700
Data Index: 3973254 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.8179. Min Act: -0.1700
Data Index: 3867826 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.7242. Min Act: -0.1700
Data Index: 3867827 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.6617. Min Act: -0.1700
Data Index: 3118868 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.4429. Min Act: -0.1700
Data Index: 5240720 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.4429. Min Act: -0.1700
Data Index: 3457656 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.4117. Min Act: -0.1700
Data Index: 7722623 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.4117. Min Act: -0.1700
Data Index: 5208826 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.3492. Min Act: -0.1700
Data Index: 2249287 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.3804. Min Act: -0.1700
Data Index: 7870974 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.3179. Min Act: -0.1700
Data Index: 4477441 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.3179. Min Act: -0.1700
Data Index: 8570325 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.2867. Min Act: -0.1700
Data Index: 6681118 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.2242. Min Act: -0.1700
Data Index: 3222818 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.2554. Min Act: -0.1700
Data Index: 2013178 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.2554. Min Act: -0.1700
Data Index: 3070740 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.2554. Min Act: -0.1700
Data Index: 6697450 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.2242. Min Act: -0.1700
Data Index: 8686909 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9742. Min Range: -6.9742
Max Act: 6.2242. Min Act: -0.1700
Data Index: 1633124 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19