Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6629. Min Range: -6.6629
Max Act: 6.6629. Min Act: -0.1700
Data Index: 6128810 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.9442. Min Act: -0.1700
Data Index: 6194605 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.8504. Min Act: -0.1700
Data Index: 216287 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.8504. Min Act: -0.1700
Data Index: 6768810 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.8192. Min Act: -0.1700
Data Index: 5289475 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.7879. Min Act: -0.1700
Data Index: 5443756 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.7567. Min Act: -0.1700
Data Index: 4499798 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.7567. Min Act: -0.1700
Data Index: 701524 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.7254. Min Act: -0.1700
Data Index: 1075071 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.7254. Min Act: -0.1700
Data Index: 1239163 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.7254. Min Act: -0.1700
Data Index: 728749 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.6942. Min Act: -0.1700
Data Index: 1714000 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.6629. Min Act: -0.1700
Data Index: 4460061 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.6317. Min Act: -0.1700
Data Index: 3638492 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.6317. Min Act: -0.1700
Data Index: 6603965 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.6004. Min Act: -0.1700
Data Index: 584683 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.6004. Min Act: -0.1700
Data Index: 777521 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.6004. Min Act: -0.1700
Data Index: 8007509 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.6004. Min Act: -0.1700
Data Index: 680621 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6629. Min Range: -6.6629
Max Act: 5.5692. Min Act: -0.1700
Data Index: 7580229 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19