Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4276 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.7517. Min Act: -0.1700
Data Index: 2560486 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.6267. Min Act: -0.1700
Data Index: 228228 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.6579. Min Act: -0.1700
Data Index: 5286428 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.4704. Min Act: -0.1700
Data Index: 4816497 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.5017. Min Act: -0.1700
Data Index: 4397405 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.4079. Min Act: -0.1700
Data Index: 7265666 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.4392. Min Act: -0.1700
Data Index: 5048518 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.2829. Min Act: -0.1700
Data Index: 661249 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.2204. Min Act: -0.1700
Data Index: 6523871 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.2517. Min Act: -0.1700
Data Index: 2291005 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.2517. Min Act: -0.1700
Data Index: 6300035 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.2204. Min Act: -0.1700
Data Index: 8382926 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.2204. Min Act: -0.1700
Data Index: 4105288 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.1892. Min Act: -0.1700
Data Index: 2050129 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.1892. Min Act: -0.1700
Data Index: 7910178 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.1892. Min Act: -0.1700
Data Index: 1266884 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.2204. Min Act: -0.1700
Data Index: 3065389 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.2204. Min Act: -0.1700
Data Index: 4018000 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.1579. Min Act: -0.1700
Data Index: 3198340 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7517. Min Range: -7.7517
Max Act: 7.1579. Min Act: -0.1700
Data Index: 7814188 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19