Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4980 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.4524. Min Act: -0.1700
Data Index: 8153027 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.3899. Min Act: -0.1700
Data Index: 3686238 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.1399. Min Act: -0.1700
Data Index: 3582002 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.1399. Min Act: -0.1700
Data Index: 35863 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.1086. Min Act: -0.1700
Data Index: 5877660 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.1086. Min Act: -0.1700
Data Index: 5389415 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.0774. Min Act: -0.1700
Data Index: 229216 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.1086. Min Act: -0.1700
Data Index: 3328048 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.1086. Min Act: -0.1700
Data Index: 3813817 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.0774. Min Act: -0.1700
Data Index: 7590242 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.1086. Min Act: -0.1700
Data Index: 3633875 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.0774. Min Act: -0.1700
Data Index: 7269363 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.0774. Min Act: -0.1700
Data Index: 1843767 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.0774. Min Act: -0.1700
Data Index: 1701121 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.0774. Min Act: -0.1700
Data Index: 7795253 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.0774. Min Act: -0.1700
Data Index: 5957753 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.0149. Min Act: -0.1700
Data Index: 5340689 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.0149. Min Act: -0.1700
Data Index: 6451657 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4524. Min Range: -5.4524
Max Act: 4.9836. Min Act: -0.1700
Data Index: 6937272 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4524. Min Range: -5.4524
Max Act: 5.0149. Min Act: -0.1700
Data Index: 3414574 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19