Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2343 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2847. Min Range: -7.2847
Max Act: 7.2847. Min Act: -0.1700
Data Index: 3976159 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2847. Min Range: -7.2847
Max Act: 7.2222. Min Act: -0.1700
Data Index: 5536289 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2847. Min Range: -7.2847
Max Act: 7.0660. Min Act: -0.1700
Data Index: 7693408 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2847. Min Range: -7.2847
Max Act: 7.0660. Min Act: -0.1700
Data Index: 6755435 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2847. Min Range: -7.2847
Max Act: 7.0347. Min Act: -0.1700
Data Index: 5901351 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.9722. Min Act: -0.1700
Data Index: 514778 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.9722. Min Act: -0.1700
Data Index: 6381829 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.9410. Min Act: -0.1700
Data Index: 5215469 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.9097. Min Act: -0.1700
Data Index: 5539733 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.8785. Min Act: -0.1700
Data Index: 5168826 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.8472. Min Act: -0.1700
Data Index: 6913824 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.8160. Min Act: -0.1700
Data Index: 2165098 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.8472. Min Act: -0.1700
Data Index: 8377438 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.7847. Min Act: -0.1700
Data Index: 7600651 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.8160. Min Act: -0.1700
Data Index: 4723029 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.7847. Min Act: -0.1700
Data Index: 8151256 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.7847. Min Act: -0.1700
Data Index: 2210688 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.7535. Min Act: -0.1700
Data Index: 7568446 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.7847. Min Act: -0.1700
Data Index: 4742687 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2847. Min Range: -7.2847
Max Act: 6.7535. Min Act: -0.1700
Data Index: 5594817 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19