Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1346 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2131. Min Range: -11.2131
Max Act: 11.2131. Min Act: -0.1700
Data Index: 1375378 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.7756. Min Act: -0.1700
Data Index: 7512913 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.7131. Min Act: -0.1700
Data Index: 7332514 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.7131. Min Act: -0.1700
Data Index: 5785714 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.7131. Min Act: -0.1700
Data Index: 7805400 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.5881. Min Act: -0.1700
Data Index: 1975939 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.5881. Min Act: -0.1700
Data Index: 8624913 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.5881. Min Act: -0.1700
Data Index: 7024616 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.5881. Min Act: -0.1700
Data Index: 1478722 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.5881. Min Act: -0.1700
Data Index: 2967857 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.5881. Min Act: -0.1700
Data Index: 6435036 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.5256. Min Act: -0.1700
Data Index: 2703164 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.5256. Min Act: -0.1700
Data Index: 7512647 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.5256. Min Act: -0.1700
Data Index: 6778732 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.4631. Min Act: -0.1700
Data Index: 537843 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.4631. Min Act: -0.1700
Data Index: 7027151 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.4006. Min Act: -0.1700
Data Index: 1522570 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.4006. Min Act: -0.1700
Data Index: 7811654 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.4631. Min Act: -0.1700
Data Index: 6360273 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2131. Min Range: -11.2131
Max Act: 10.4006. Min Act: -0.1700
Data Index: 8321112 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19