Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2362 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.7879. Min Act: -0.1700
Data Index: 8806878 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.7567. Min Act: -0.1700
Data Index: 5453830 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.7567. Min Act: -0.1700
Data Index: 7980179 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.7567. Min Act: -0.1700
Data Index: 472247 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.7567. Min Act: -0.1700
Data Index: 6267423 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.7254. Min Act: -0.1700
Data Index: 832228 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6942. Min Act: -0.1700
Data Index: 2141569 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6942. Min Act: -0.1700
Data Index: 3375619 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6942. Min Act: -0.1700
Data Index: 6224741 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6942. Min Act: -0.1700
Data Index: 8806881 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6317. Min Act: -0.1700
Data Index: 6466327 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6629. Min Act: -0.1700
Data Index: 1775117 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6629. Min Act: -0.1700
Data Index: 5453828 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6629. Min Act: -0.1700
Data Index: 6348425 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6004. Min Act: -0.1700
Data Index: 472245 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6317. Min Act: -0.1700
Data Index: 6369835 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6317. Min Act: -0.1700
Data Index: 6348423 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6317. Min Act: -0.1700
Data Index: 6369834 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6317. Min Act: -0.1700
Data Index: 6369833 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7879. Min Range: -4.7879
Max Act: 4.6004. Min Act: -0.1700
Data Index: 832226 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19