Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3480 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0543. Min Range: -8.0543
Max Act: 8.0543. Min Act: -0.1700
Data Index: 2356133 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.8043. Min Act: -0.1700
Data Index: 1990716 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.5856. Min Act: -0.1700
Data Index: 3055422 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.4918. Min Act: -0.1700
Data Index: 8015360 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.4606. Min Act: -0.1700
Data Index: 7535805 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.4293. Min Act: -0.1700
Data Index: 3867168 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.3356. Min Act: -0.1700
Data Index: 1327008 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.3668. Min Act: -0.1700
Data Index: 6771968 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.3356. Min Act: -0.1700
Data Index: 3890923 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.3043. Min Act: -0.1700
Data Index: 2625161 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.3043. Min Act: -0.1700
Data Index: 425514 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.2731. Min Act: -0.1700
Data Index: 5614555 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.2731. Min Act: -0.1700
Data Index: 1598446 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.2106. Min Act: -0.1700
Data Index: 2101726 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.2418. Min Act: -0.1700
Data Index: 8457379 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.1793. Min Act: -0.1700
Data Index: 8290926 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.1793. Min Act: -0.1700
Data Index: 8694400 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.1481. Min Act: -0.1700
Data Index: 5136524 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.1481. Min Act: -0.1700
Data Index: 2022188 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0543. Min Range: -8.0543
Max Act: 7.1481. Min Act: -0.1700
Data Index: 551466 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19