Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5348 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.7297. Min Act: -0.1700
Data Index: 8165463 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.6672. Min Act: -0.1700
Data Index: 1074590 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.6672. Min Act: -0.1700
Data Index: 767113 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.6047. Min Act: -0.1700
Data Index: 5591341 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.5422. Min Act: -0.1700
Data Index: 1421028 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.5422. Min Act: -0.1700
Data Index: 7384749 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.4797. Min Act: -0.1700
Data Index: 594366 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.4797. Min Act: -0.1700
Data Index: 5433084 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.4172. Min Act: -0.1700
Data Index: 8826832 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.4172. Min Act: -0.1700
Data Index: 3343620 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.3547. Min Act: -0.1700
Data Index: 4987408 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.3547. Min Act: -0.1700
Data Index: 5316444 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.2922. Min Act: -0.1700
Data Index: 7921786 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.3547. Min Act: -0.1700
Data Index: 5402279 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.2297. Min Act: -0.1700
Data Index: 3105501 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.2922. Min Act: -0.1700
Data Index: 1960090 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.2297. Min Act: -0.1700
Data Index: 5866856 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.2297. Min Act: -0.1700
Data Index: 5202702 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.2297. Min Act: -0.1700
Data Index: 418810 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7297. Min Range: -8.7297
Max Act: 8.2297. Min Act: -0.1700
Data Index: 1767419 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19