Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 935 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1457. Min Range: -8.1457
Max Act: 8.1457. Min Act: -0.1700
Data Index: 4996362 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.4582. Min Act: -0.1700
Data Index: 1181963 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.3020. Min Act: -0.1700
Data Index: 8734699 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.2707. Min Act: -0.1700
Data Index: 3298999 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.2082. Min Act: -0.1700
Data Index: 7032407 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.1457. Min Act: -0.1700
Data Index: 8228319 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.1770. Min Act: -0.1700
Data Index: 8234883 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.1457. Min Act: -0.1700
Data Index: 3047134 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.1457. Min Act: -0.1700
Data Index: 8665266 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.0832. Min Act: -0.1700
Data Index: 1481422 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.0520. Min Act: -0.1700
Data Index: 6358147 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.0520. Min Act: -0.1700
Data Index: 6815917 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.0520. Min Act: -0.1700
Data Index: 7922749 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.0207. Min Act: -0.1700
Data Index: 8558048 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.0207. Min Act: -0.1700
Data Index: 1214184 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.0207. Min Act: -0.1700
Data Index: 298890 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.0520. Min Act: -0.1700
Data Index: 4406654 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.0207. Min Act: -0.1700
Data Index: 451194 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1457. Min Range: -8.1457
Max Act: 7.0207. Min Act: -0.1700
Data Index: 2218902 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1457. Min Range: -8.1457
Max Act: 6.9895. Min Act: -0.1700
Data Index: 1226209 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19