Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4248 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.3906. Min Act: -0.1700
Data Index: 2890434 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.2968. Min Act: -0.1700
Data Index: 3050897 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.2343. Min Act: -0.1700
Data Index: 5573921 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.2343. Min Act: -0.1700
Data Index: 5768402 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1406. Min Act: -0.1700
Data Index: 7624784 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1718. Min Act: -0.1700
Data Index: 5189935 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1406. Min Act: -0.1700
Data Index: 1339235 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1406. Min Act: -0.1700
Data Index: 421219 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1406. Min Act: -0.1700
Data Index: 3952835 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1093. Min Act: -0.1700
Data Index: 4480756 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.0468. Min Act: -0.1700
Data Index: 1019942 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.0781. Min Act: -0.1700
Data Index: 2162430 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.0468. Min Act: -0.1700
Data Index: 765982 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.0468. Min Act: -0.1700
Data Index: 1507945 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3906. Min Range: -5.3906
Max Act: 4.9843. Min Act: -0.1700
Data Index: 2683751 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3906. Min Range: -5.3906
Max Act: 4.9843. Min Act: -0.1700
Data Index: 1907194 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3906. Min Range: -5.3906
Max Act: 4.9531. Min Act: -0.1700
Data Index: 3671068 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3906. Min Range: -5.3906
Max Act: 4.9843. Min Act: -0.1700
Data Index: 4575683 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3906. Min Range: -5.3906
Max Act: 4.9843. Min Act: -0.1700
Data Index: 6663239 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3906. Min Range: -5.3906
Max Act: 4.9843. Min Act: -0.1700
Data Index: 4940982 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19