Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3152 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3734. Min Range: -7.3734
Max Act: 7.3734. Min Act: -0.1700
Data Index: 2065163 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3734. Min Range: -7.3734
Max Act: 7.1859. Min Act: -0.1700
Data Index: 1959778 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.9672. Min Act: -0.1700
Data Index: 6893554 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.9984. Min Act: -0.1700
Data Index: 8077819 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.7797. Min Act: -0.1700
Data Index: 5611362 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.6547. Min Act: -0.1700
Data Index: 6886389 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.5922. Min Act: -0.1700
Data Index: 6481990 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.5297. Min Act: -0.1700
Data Index: 7398071 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.4984. Min Act: -0.1700
Data Index: 2771607 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.4359. Min Act: -0.1700
Data Index: 232302 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.4984. Min Act: -0.1700
Data Index: 766822 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.4359. Min Act: -0.1700
Data Index: 5736792 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.4047. Min Act: -0.1700
Data Index: 4933229 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.3422. Min Act: -0.1700
Data Index: 6297895 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.2797. Min Act: -0.1700
Data Index: 1574586 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.2797. Min Act: -0.1700
Data Index: 5497332 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.3109. Min Act: -0.1700
Data Index: 5088015 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.2484. Min Act: -0.1700
Data Index: 8294251 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.2172. Min Act: -0.1700
Data Index: 6291653 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3734. Min Range: -7.3734
Max Act: 6.2172. Min Act: -0.1700
Data Index: 550700 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19