Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 852 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.1318. Min Act: -0.1700
Data Index: 3564927 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.1006. Min Act: -0.1700
Data Index: 1163757 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9756. Min Act: -0.1700
Data Index: 3991264 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.8193. Min Act: -0.1700
Data Index: 8125242 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.8193. Min Act: -0.1700
Data Index: 1072003 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.7881. Min Act: -0.1700
Data Index: 4061609 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.7881. Min Act: -0.1700
Data Index: 2325144 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.7256. Min Act: -0.1700
Data Index: 6582601 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.7568. Min Act: -0.1700
Data Index: 7144775 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.6943. Min Act: -0.1700
Data Index: 6011361 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.7256. Min Act: -0.1700
Data Index: 8148451 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.6943. Min Act: -0.1700
Data Index: 5339004 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.6631. Min Act: -0.1700
Data Index: 2325142 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.6943. Min Act: -0.1700
Data Index: 4180302 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.6631. Min Act: -0.1700
Data Index: 5735984 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.6318. Min Act: -0.1700
Data Index: 5511863 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.6631. Min Act: -0.1700
Data Index: 7890098 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.6318. Min Act: -0.1700
Data Index: 97109 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.6318. Min Act: -0.1700
Data Index: 54901 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.6318. Min Act: -0.1700
Data Index: 1941088 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19