Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6398 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.7672. Min Act: -0.1700
Data Index: 7775782 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.7047. Min Act: -0.1700
Data Index: 709982 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.6734. Min Act: -0.1700
Data Index: 4568874 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.6734. Min Act: -0.1700
Data Index: 1292698 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.6421. Min Act: -0.1700
Data Index: 3783612 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.6421. Min Act: -0.1700
Data Index: 1227450 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.6421. Min Act: -0.1700
Data Index: 1201392 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.6421. Min Act: -0.1700
Data Index: 8671001 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.6421. Min Act: -0.1700
Data Index: 6021938 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.6108. Min Act: -0.1700
Data Index: 8066245 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.6108. Min Act: -0.1700
Data Index: 2143 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.6108. Min Act: -0.1700
Data Index: 7920401 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.6108. Min Act: -0.1700
Data Index: 4568877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.5951. Min Act: -0.1700
Data Index: 3911928 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.5951. Min Act: -0.1700
Data Index: 6184406 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.5951. Min Act: -0.1700
Data Index: 2869260 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.5795. Min Act: -0.1700
Data Index: 6380370 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.5638. Min Act: -0.1700
Data Index: 7339314 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.5795. Min Act: -0.1700
Data Index: 3676289 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7672. Min Range: -3.7672
Max Act: 3.5795. Min Act: -0.1700
Data Index: 7557249 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19