Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1660. Min Range: -3.1660
Max Act: 3.1660. Min Act: -0.1700
Data Index: 226768 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1660. Min Range: -3.1660
Max Act: 3.1030. Min Act: -0.1700
Data Index: 7688950 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1660. Min Range: -3.1660
Max Act: 3.0872. Min Act: -0.1700
Data Index: 1507731 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1660. Min Range: -3.1660
Max Act: 3.0872. Min Act: -0.1700
Data Index: 178186 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1660. Min Range: -3.1660
Max Act: 3.0872. Min Act: -0.1700
Data Index: 4965602 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1660. Min Range: -3.1660
Max Act: 3.0557. Min Act: -0.1700
Data Index: 6070259 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1660. Min Range: -3.1660
Max Act: 3.0399. Min Act: -0.1700
Data Index: 6932356 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1660. Min Range: -3.1660
Max Act: 3.0241. Min Act: -0.1700
Data Index: 3152649 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1660. Min Range: -3.1660
Max Act: 3.0083. Min Act: -0.1700
Data Index: 824070 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1660. Min Range: -3.1660
Max Act: 3.0083. Min Act: -0.1700
Data Index: 824066 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1660. Min Range: -3.1660
Max Act: 3.0241. Min Act: -0.1700
Data Index: 3741852 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1660. Min Range: -3.1660
Max Act: 2.9925. Min Act: -0.1700
Data Index: 2098336 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1660. Min Range: -3.1660
Max Act: 2.9925. Min Act: -0.1700
Data Index: 4619273 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1660. Min Range: -3.1660
Max Act: 2.9925. Min Act: -0.1700
Data Index: 8635679 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1660. Min Range: -3.1660
Max Act: 2.9609. Min Act: -0.1700
Data Index: 3582378 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1660. Min Range: -3.1660
Max Act: 2.9767. Min Act: -0.1700
Data Index: 215514 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1660. Min Range: -3.1660
Max Act: 2.9451. Min Act: -0.1700
Data Index: 6108922 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1660. Min Range: -3.1660
Max Act: 2.9609. Min Act: -0.1700
Data Index: 1477698 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1660. Min Range: -3.1660
Max Act: 2.9609. Min Act: -0.1700
Data Index: 1665034 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1660. Min Range: -3.1660
Max Act: 2.9609. Min Act: -0.1700
Data Index: 5104383 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19