Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4784. Min Range: -10.4784
Max Act: 10.4784. Min Act: -0.1700
Data Index: 4714810 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4784. Min Range: -10.4784
Max Act: 10.1659. Min Act: -0.1700
Data Index: 6157677 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4784. Min Range: -10.4784
Max Act: 9.6659. Min Act: -0.1700
Data Index: 6323751 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4784. Min Range: -10.4784
Max Act: 9.7284. Min Act: -0.1700
Data Index: 3430032 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4784. Min Range: -10.4784
Max Act: 9.6034. Min Act: -0.1700
Data Index: 4268888 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4784. Min Range: -10.4784
Max Act: 9.5409. Min Act: -0.1700
Data Index: 4360782 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4784. Min Range: -10.4784
Max Act: 9.3534. Min Act: -0.1700
Data Index: 7154220 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4784. Min Range: -10.4784
Max Act: 9.2909. Min Act: -0.1700
Data Index: 2182 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4784. Min Range: -10.4784
Max Act: 9.2284. Min Act: -0.1700
Data Index: 5343266 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4784. Min Range: -10.4784
Max Act: 9.1034. Min Act: -0.1700
Data Index: 8217654 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4784. Min Range: -10.4784
Max Act: 9.1034. Min Act: -0.1700
Data Index: 1513409 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4784. Min Range: -10.4784
Max Act: 9.1034. Min Act: -0.1700
Data Index: 6676127 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4784. Min Range: -10.4784
Max Act: 8.9784. Min Act: -0.1700
Data Index: 4135395 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4784. Min Range: -10.4784
Max Act: 8.8534. Min Act: -0.1700
Data Index: 4263385 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4784. Min Range: -10.4784
Max Act: 8.4784. Min Act: -0.1700
Data Index: 484644 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4784. Min Range: -10.4784
Max Act: 8.1659. Min Act: -0.1700
Data Index: 4005127 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4784. Min Range: -10.4784
Max Act: 8.0721. Min Act: -0.1700
Data Index: 8337321 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4784. Min Range: -10.4784
Max Act: 7.9471. Min Act: -0.1700
Data Index: 5256511 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4784. Min Range: -10.4784
Max Act: 7.7596. Min Act: -0.1700
Data Index: 3114013 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4784. Min Range: -10.4784
Max Act: 7.7596. Min Act: -0.1700
Data Index: 7490149 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19