Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 456 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.6528. Min Act: -0.1700
Data Index: 6857094 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.6215. Min Act: -0.1700
Data Index: 4962137 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.6215. Min Act: -0.1700
Data Index: 1854145 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.5590. Min Act: -0.1700
Data Index: 5695633 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.5278. Min Act: -0.1700
Data Index: 898911 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4965. Min Act: -0.1700
Data Index: 3101493 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4965. Min Act: -0.1700
Data Index: 352189 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4965. Min Act: -0.1700
Data Index: 3786617 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4653. Min Act: -0.1700
Data Index: 5784524 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4653. Min Act: -0.1700
Data Index: 5892835 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4653. Min Act: -0.1700
Data Index: 4676485 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4653. Min Act: -0.1700
Data Index: 7306938 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4340. Min Act: -0.1700
Data Index: 3114140 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4340. Min Act: -0.1700
Data Index: 3520086 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4340. Min Act: -0.1700
Data Index: 5109012 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4340. Min Act: -0.1700
Data Index: 2991948 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4028. Min Act: -0.1700
Data Index: 5091974 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4028. Min Act: -0.1700
Data Index: 5443802 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4028. Min Act: -0.1700
Data Index: 198334 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6528. Min Range: -4.6528
Max Act: 4.4028. Min Act: -0.1700
Data Index: 1758569 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19