Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1251 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0580. Min Range: -3.0580
Max Act: 3.0580. Min Act: -0.1700
Data Index: 1239783 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0580. Min Range: -3.0580
Max Act: 3.0423. Min Act: -0.1700
Data Index: 5631658 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0580. Min Range: -3.0580
Max Act: 3.0423. Min Act: -0.1700
Data Index: 6716441 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0580. Min Range: -3.0580
Max Act: 3.0265. Min Act: -0.1700
Data Index: 2573972 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0580. Min Range: -3.0580
Max Act: 3.0265. Min Act: -0.1700
Data Index: 787469 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0580. Min Range: -3.0580
Max Act: 3.0107. Min Act: -0.1700
Data Index: 5585087 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0580. Min Range: -3.0580
Max Act: 3.0107. Min Act: -0.1700
Data Index: 402608 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0580. Min Range: -3.0580
Max Act: 3.0107. Min Act: -0.1700
Data Index: 104674 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0580. Min Range: -3.0580
Max Act: 3.0107. Min Act: -0.1700
Data Index: 1892568 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0580. Min Range: -3.0580
Max Act: 3.0107. Min Act: -0.1700
Data Index: 5395996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0580. Min Range: -3.0580
Max Act: 3.0107. Min Act: -0.1700
Data Index: 8134858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0580. Min Range: -3.0580
Max Act: 2.9949. Min Act: -0.1700
Data Index: 6670655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0580. Min Range: -3.0580
Max Act: 2.9949. Min Act: -0.1700
Data Index: 2718427 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0580. Min Range: -3.0580
Max Act: 2.9949. Min Act: -0.1700
Data Index: 3773817 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0580. Min Range: -3.0580
Max Act: 2.9949. Min Act: -0.1700
Data Index: 6048415 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0580. Min Range: -3.0580
Max Act: 2.9949. Min Act: -0.1700
Data Index: 3926643 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0580. Min Range: -3.0580
Max Act: 2.9949. Min Act: -0.1700
Data Index: 4146684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0580. Min Range: -3.0580
Max Act: 2.9949. Min Act: -0.1700
Data Index: 1411663 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0580. Min Range: -3.0580
Max Act: 2.9949. Min Act: -0.1700
Data Index: 4114421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0580. Min Range: -3.0580
Max Act: 2.9949. Min Act: -0.1700
Data Index: 2992579 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19