Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2296. Min Range: -5.2296
Max Act: 5.2296. Min Act: -0.1700
Data Index: 711965 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2296. Min Range: -5.2296
Max Act: 5.1046. Min Act: -0.1700
Data Index: 2817041 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2296. Min Range: -5.2296
Max Act: 5.0108. Min Act: -0.1700
Data Index: 7623231 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.9483. Min Act: -0.1700
Data Index: 4758997 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.9171. Min Act: -0.1700
Data Index: 4660914 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.8546. Min Act: -0.1700
Data Index: 278897 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.8233. Min Act: -0.1700
Data Index: 583928 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.8233. Min Act: -0.1700
Data Index: 1679130 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.8546. Min Act: -0.1700
Data Index: 3436609 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.8233. Min Act: -0.1700
Data Index: 1658854 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.7921. Min Act: -0.1700
Data Index: 7097919 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.7608. Min Act: -0.1700
Data Index: 8023776 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.7608. Min Act: -0.1700
Data Index: 6638633 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.7608. Min Act: -0.1700
Data Index: 7456981 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.7608. Min Act: -0.1700
Data Index: 2315384 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.7608. Min Act: -0.1700
Data Index: 6255475 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.7608. Min Act: -0.1700
Data Index: 83995 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.7608. Min Act: -0.1700
Data Index: 1989748 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.7608. Min Act: -0.1700
Data Index: 2270669 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2296. Min Range: -5.2296
Max Act: 4.7608. Min Act: -0.1700
Data Index: 3017887 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19