Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.6530. Min Act: -0.1700
Data Index: 7673886 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.6218. Min Act: -0.1700
Data Index: 4892712 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.5905. Min Act: -0.1700
Data Index: 7775004 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.5905. Min Act: -0.1700
Data Index: 3920384 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.5280. Min Act: -0.1700
Data Index: 251000 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4968. Min Act: -0.1700
Data Index: 3204639 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4968. Min Act: -0.1700
Data Index: 7892249 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.5280. Min Act: -0.1700
Data Index: 1877470 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4968. Min Act: -0.1700
Data Index: 3001284 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4968. Min Act: -0.1700
Data Index: 7529013 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4655. Min Act: -0.1700
Data Index: 754538 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4655. Min Act: -0.1700
Data Index: 3970763 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4655. Min Act: -0.1700
Data Index: 7034739 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4655. Min Act: -0.1700
Data Index: 3371341 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4655. Min Act: -0.1700
Data Index: 3239589 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4655. Min Act: -0.1700
Data Index: 1040149 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4343. Min Act: -0.1700
Data Index: 6422928 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4343. Min Act: -0.1700
Data Index: 5621118 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4343. Min Act: -0.1700
Data Index: 4721488 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6530. Min Range: -4.6530
Max Act: 4.4343. Min Act: -0.1700
Data Index: 3208631 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19