Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4598 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1628. Min Range: -5.1628
Max Act: 5.1628. Min Act: -0.1700
Data Index: 1848065 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1628. Min Range: -5.1628
Max Act: 5.1315. Min Act: -0.1700
Data Index: 1155782 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.9753. Min Act: -0.1700
Data Index: 4174062 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.8503. Min Act: -0.1700
Data Index: 8056850 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.8503. Min Act: -0.1700
Data Index: 6520755 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.7878. Min Act: -0.1700
Data Index: 7736512 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.7565. Min Act: -0.1700
Data Index: 1418837 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.7565. Min Act: -0.1700
Data Index: 1096590 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.7565. Min Act: -0.1700
Data Index: 5833615 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.7565. Min Act: -0.1700
Data Index: 5057278 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.7565. Min Act: -0.1700
Data Index: 5574142 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.7253. Min Act: -0.1700
Data Index: 3946143 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.6940. Min Act: -0.1700
Data Index: 7489948 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.7253. Min Act: -0.1700
Data Index: 5057279 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.7253. Min Act: -0.1700
Data Index: 6663508 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.6940. Min Act: -0.1700
Data Index: 2807250 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.6940. Min Act: -0.1700
Data Index: 3855940 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.6940. Min Act: -0.1700
Data Index: 7032423 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.6628. Min Act: -0.1700
Data Index: 4204682 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1628. Min Range: -5.1628
Max Act: 4.6628. Min Act: -0.1700
Data Index: 4524937 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19