Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3864 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.4507. Min Act: -0.1700
Data Index: 141789 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.4507. Min Act: -0.1700
Data Index: 6003904 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.2632. Min Act: -0.1700
Data Index: 3239648 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.2319. Min Act: -0.1700
Data Index: 8117906 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.2007. Min Act: -0.1700
Data Index: 2541767 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.2319. Min Act: -0.1700
Data Index: 5948103 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.2007. Min Act: -0.1700
Data Index: 1408546 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.2007. Min Act: -0.1700
Data Index: 8096098 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.2007. Min Act: -0.1700
Data Index: 4526980 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.1694. Min Act: -0.1700
Data Index: 1256798 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.1382. Min Act: -0.1700
Data Index: 6814674 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.1382. Min Act: -0.1700
Data Index: 2831317 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.1382. Min Act: -0.1700
Data Index: 5238536 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.1069. Min Act: -0.1700
Data Index: 2548309 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.1069. Min Act: -0.1700
Data Index: 5275607 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.1069. Min Act: -0.1700
Data Index: 8437247 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.1382. Min Act: -0.1700
Data Index: 3288350 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.0444. Min Act: -0.1700
Data Index: 6519989 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.0444. Min Act: -0.1700
Data Index: 3706899 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4507. Min Range: -7.4507
Max Act: 7.0444. Min Act: -0.1700
Data Index: 6639330 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19