Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6343 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.2832. Min Act: -0.1700
Data Index: 8058698 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.2203. Min Act: -0.1700
Data Index: 5480643 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.2203. Min Act: -0.1700
Data Index: 2353387 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1889. Min Act: -0.1700
Data Index: 304819 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1731. Min Act: -0.1700
Data Index: 237295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1731. Min Act: -0.1700
Data Index: 5097350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1574. Min Act: -0.1700
Data Index: 6415396 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1574. Min Act: -0.1700
Data Index: 7447255 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1574. Min Act: -0.1700
Data Index: 144266 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1574. Min Act: -0.1700
Data Index: 2097161 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1574. Min Act: -0.1700
Data Index: 5107439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1574. Min Act: -0.1700
Data Index: 4924184 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1574. Min Act: -0.1700
Data Index: 419501 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1417. Min Act: -0.1700
Data Index: 4600050 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1417. Min Act: -0.1700
Data Index: 2274333 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1417. Min Act: -0.1700
Data Index: 7935581 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1574. Min Act: -0.1700
Data Index: 4378127 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1417. Min Act: -0.1700
Data Index: 7802728 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1417. Min Act: -0.1700
Data Index: 5502847 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2832. Min Range: -3.2832
Max Act: 3.1417. Min Act: -0.1700
Data Index: 4630082 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19