Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4074 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1381. Min Range: -7.1381
Max Act: 7.1381. Min Act: -0.1700
Data Index: 2340292 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1381. Min Range: -7.1381
Max Act: 7.1068. Min Act: -0.1700
Data Index: 8541082 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1381. Min Range: -7.1381
Max Act: 7.0756. Min Act: -0.1700
Data Index: 4531984 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.9818. Min Act: -0.1700
Data Index: 5853422 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.9818. Min Act: -0.1700
Data Index: 1747226 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.9818. Min Act: -0.1700
Data Index: 8153688 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.8568. Min Act: -0.1700
Data Index: 3719412 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.7943. Min Act: -0.1700
Data Index: 4625371 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.8256. Min Act: -0.1700
Data Index: 2845080 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.7631. Min Act: -0.1700
Data Index: 8608029 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.7318. Min Act: -0.1700
Data Index: 4350745 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.7006. Min Act: -0.1700
Data Index: 4032628 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.7318. Min Act: -0.1700
Data Index: 4299960 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.6693. Min Act: -0.1700
Data Index: 3209496 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.6693. Min Act: -0.1700
Data Index: 3038565 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.6693. Min Act: -0.1700
Data Index: 102122 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.6381. Min Act: -0.1700
Data Index: 3612566 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.6381. Min Act: -0.1700
Data Index: 24303 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.6381. Min Act: -0.1700
Data Index: 6287531 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1381. Min Range: -7.1381
Max Act: 6.5756. Min Act: -0.1700
Data Index: 1357780 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19