Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.3778. Min Act: -0.1699
Data Index: 5847340 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.3249. Min Act: -0.1686
Data Index: 3065513 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.3073. Min Act: -0.1688
Data Index: 835767 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2720. Min Act: -0.1700
Data Index: 1141262 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2896. Min Act: -0.1700
Data Index: 1090862 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2720. Min Act: -0.1697
Data Index: 121326 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2720. Min Act: -0.1685
Data Index: 3034834 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2720. Min Act: -0.1700
Data Index: 6184566 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2720. Min Act: -0.1699
Data Index: 1406383 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2544. Min Act: -0.1700
Data Index: 5413075 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2720. Min Act: -0.1700
Data Index: 3884842 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2720. Min Act: -0.1606
Data Index: 7555853 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2720. Min Act: -0.1695
Data Index: 7054983 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2544. Min Act: -0.1582
Data Index: 629424 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2191. Min Act: -0.1700
Data Index: 300690 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2367. Min Act: -0.1582
Data Index: 873863 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2367. Min Act: -0.1654
Data Index: 2576214 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2367. Min Act: -0.1669
Data Index: 4131011 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2367. Min Act: -0.1619
Data Index: 3271362 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3778. Min Range: -1.3778
Max Act: 1.2367. Min Act: -0.1700
Data Index: 6593105 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19