Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2444 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5409. Min Range: -6.5409
Max Act: 6.5409. Min Act: -0.1700
Data Index: 1726880 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5409. Min Range: -6.5409
Max Act: 6.2909. Min Act: -0.1700
Data Index: 7948504 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5409. Min Range: -6.5409
Max Act: 6.2284. Min Act: -0.1700
Data Index: 7230335 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5409. Min Range: -6.5409
Max Act: 6.1346. Min Act: -0.1700
Data Index: 2197596 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5409. Min Range: -6.5409
Max Act: 6.1034. Min Act: -0.1700
Data Index: 2063257 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5409. Min Range: -6.5409
Max Act: 6.0721. Min Act: -0.1700
Data Index: 6561726 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5409. Min Range: -6.5409
Max Act: 6.0721. Min Act: -0.1700
Data Index: 7230339 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5409. Min Range: -6.5409
Max Act: 6.0721. Min Act: -0.1700
Data Index: 8717182 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5409. Min Range: -6.5409
Max Act: 6.0409. Min Act: -0.1700
Data Index: 6448293 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5409. Min Range: -6.5409
Max Act: 5.9471. Min Act: -0.1700
Data Index: 3247403 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5409. Min Range: -6.5409
Max Act: 5.8846. Min Act: -0.1700
Data Index: 2022482 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5409. Min Range: -6.5409
Max Act: 5.9159. Min Act: -0.1700
Data Index: 1560717 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5409. Min Range: -6.5409
Max Act: 5.9159. Min Act: -0.1700
Data Index: 4641403 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5409. Min Range: -6.5409
Max Act: 5.8846. Min Act: -0.1700
Data Index: 4190620 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5409. Min Range: -6.5409
Max Act: 5.8534. Min Act: -0.1700
Data Index: 3559989 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5409. Min Range: -6.5409
Max Act: 5.8221. Min Act: -0.1700
Data Index: 584027 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5409. Min Range: -6.5409
Max Act: 5.8534. Min Act: -0.1700
Data Index: 7884455 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5409. Min Range: -6.5409
Max Act: 5.8534. Min Act: -0.1700
Data Index: 1546395 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5409. Min Range: -6.5409
Max Act: 5.8534. Min Act: -0.1700
Data Index: 7995940 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5409. Min Range: -6.5409
Max Act: 5.8221. Min Act: -0.1700
Data Index: 5490077 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19