Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2362 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1671. Min Range: -3.1671
Max Act: 3.1671. Min Act: -0.1700
Data Index: 660729 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.9778. Min Act: -0.1700
Data Index: 1229722 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.9778. Min Act: -0.1700
Data Index: 3519645 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.9145. Min Act: -0.1700
Data Index: 21528 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8987. Min Act: -0.1700
Data Index: 5505402 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8828. Min Act: -0.1700
Data Index: 6395419 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8510. Min Act: -0.1700
Data Index: 4823447 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8510. Min Act: -0.1700
Data Index: 6288861 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8351. Min Act: -0.1700
Data Index: 8500397 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8192. Min Act: -0.1700
Data Index: 2812640 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8192. Min Act: -0.1700
Data Index: 4159646 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8033. Min Act: -0.1700
Data Index: 1608948 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8192. Min Act: -0.1700
Data Index: 5469076 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8033. Min Act: -0.1700
Data Index: 6122951 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8033. Min Act: -0.1700
Data Index: 7597285 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8033. Min Act: -0.1700
Data Index: 930899 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.8033. Min Act: -0.1700
Data Index: 4197750 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.7715. Min Act: -0.1700
Data Index: 3714594 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.7874. Min Act: -0.1700
Data Index: 6162329 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1671. Min Range: -3.1671
Max Act: 2.7874. Min Act: -0.1700
Data Index: 6925130 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19