Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3935 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4961. Min Act: -0.1700
Data Index: 4459322 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4961. Min Act: -0.1700
Data Index: 3739495 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4649. Min Act: -0.1700
Data Index: 3650170 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4649. Min Act: -0.1700
Data Index: 8303575 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4649. Min Act: -0.1700
Data Index: 1408022 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4649. Min Act: -0.1700
Data Index: 4186536 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4336. Min Act: -0.1700
Data Index: 6105405 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4336. Min Act: -0.1700
Data Index: 8139828 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4336. Min Act: -0.1700
Data Index: 8006718 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4336. Min Act: -0.1700
Data Index: 7180055 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4336. Min Act: -0.1700
Data Index: 6931710 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4336. Min Act: -0.1700
Data Index: 1861993 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4336. Min Act: -0.1700
Data Index: 6744711 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4336. Min Act: -0.1700
Data Index: 3400685 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4336. Min Act: -0.1700
Data Index: 4810349 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4336. Min Act: -0.1700
Data Index: 4179666 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4336. Min Act: -0.1700
Data Index: 3762623 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4336. Min Act: -0.1700
Data Index: 1289352 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.3711. Min Act: -0.1700
Data Index: 768745 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4024. Min Act: -0.1700
Data Index: 2529135 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19