Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5042 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.5398. Min Act: -0.1700
Data Index: 1376491 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.5084. Min Act: -0.1700
Data Index: 2999896 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.4458. Min Act: -0.1700
Data Index: 925428 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.3987. Min Act: -0.1700
Data Index: 616271 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.3517. Min Act: -0.1700
Data Index: 1085415 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.3517. Min Act: -0.1700
Data Index: 5294191 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.3517. Min Act: -0.1700
Data Index: 287994 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.3517. Min Act: -0.1700
Data Index: 2953815 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.3203. Min Act: -0.1700
Data Index: 7479517 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.3046. Min Act: -0.1700
Data Index: 2542989 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.3046. Min Act: -0.1700
Data Index: 406451 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.2889. Min Act: -0.1700
Data Index: 4240331 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.3046. Min Act: -0.1700
Data Index: 149460 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.2732. Min Act: -0.1700
Data Index: 585732 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.2732. Min Act: -0.1700
Data Index: 4286800 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.2575. Min Act: -0.1700
Data Index: 6389933 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.2732. Min Act: -0.1700
Data Index: 2991290 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.2418. Min Act: -0.1700
Data Index: 4190567 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.2418. Min Act: -0.1700
Data Index: 891974 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5398. Min Range: -3.5398
Max Act: 3.2418. Min Act: -0.1700
Data Index: 194831 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19