Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2116 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.8517. Min Act: -0.1700
Data Index: 8610725 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.7267. Min Act: -0.1700
Data Index: 7245123 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.7267. Min Act: -0.1700
Data Index: 7697942 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.6017. Min Act: -0.1700
Data Index: 6985992 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.5392. Min Act: -0.1700
Data Index: 741143 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.5392. Min Act: -0.1700
Data Index: 7485014 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.4142. Min Act: -0.1700
Data Index: 4445145 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.3829. Min Act: -0.1700
Data Index: 7396099 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.3204. Min Act: -0.1700
Data Index: 8365670 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.2892. Min Act: -0.1700
Data Index: 2698269 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.2892. Min Act: -0.1700
Data Index: 3168924 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.3204. Min Act: -0.1700
Data Index: 320044 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.2892. Min Act: -0.1700
Data Index: 6999941 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.2579. Min Act: -0.1700
Data Index: 6562784 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.2267. Min Act: -0.1700
Data Index: 8449821 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.1954. Min Act: -0.1700
Data Index: 456519 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.1954. Min Act: -0.1700
Data Index: 3219690 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.1642. Min Act: -0.1700
Data Index: 7792246 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.1642. Min Act: -0.1700
Data Index: 6736194 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8517. Min Range: -7.8517
Max Act: 7.1954. Min Act: -0.1700
Data Index: 933142 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19