Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1824 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.5486. Min Act: -0.1700
Data Index: 7458257 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.4548. Min Act: -0.1700
Data Index: 1920039 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.4548. Min Act: -0.1700
Data Index: 7640200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.4548. Min Act: -0.1700
Data Index: 5411911 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.4548. Min Act: -0.1700
Data Index: 1502238 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.4236. Min Act: -0.1700
Data Index: 6785459 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.4236. Min Act: -0.1700
Data Index: 2597 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.4548. Min Act: -0.1700
Data Index: 19813 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.3923. Min Act: -0.1700
Data Index: 8631166 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.3611. Min Act: -0.1700
Data Index: 4650707 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.3611. Min Act: -0.1700
Data Index: 1619899 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.3611. Min Act: -0.1700
Data Index: 1917512 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.3298. Min Act: -0.1700
Data Index: 3205501 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.3298. Min Act: -0.1700
Data Index: 3686901 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.3298. Min Act: -0.1700
Data Index: 1456212 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.3298. Min Act: -0.1700
Data Index: 7014167 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.2986. Min Act: -0.1700
Data Index: 7988993 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.2986. Min Act: -0.1700
Data Index: 4557538 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.2986. Min Act: -0.1700
Data Index: 6932966 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5486. Min Range: -5.5486
Max Act: 5.3298. Min Act: -0.1700
Data Index: 5506105 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19