Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0485. Min Range: -7.0485
Max Act: 7.0485. Min Act: -0.1700
Data Index: 6272940 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.5173. Min Act: -0.1700
Data Index: 5055370 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.4548. Min Act: -0.1700
Data Index: 6922485 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.4235. Min Act: -0.1700
Data Index: 389015 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.4235. Min Act: -0.1700
Data Index: 5532011 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.3923. Min Act: -0.1700
Data Index: 1337187 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.2985. Min Act: -0.1700
Data Index: 2075280 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.2985. Min Act: -0.1700
Data Index: 987010 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.2360. Min Act: -0.1700
Data Index: 2426760 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.2048. Min Act: -0.1700
Data Index: 6320409 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.1423. Min Act: -0.1700
Data Index: 5369475 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.1735. Min Act: -0.1700
Data Index: 4907616 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.1423. Min Act: -0.1700
Data Index: 5448809 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.1735. Min Act: -0.1700
Data Index: 8034291 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.1423. Min Act: -0.1700
Data Index: 1034678 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.1423. Min Act: -0.1700
Data Index: 1779189 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.1423. Min Act: -0.1700
Data Index: 3886145 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.1110. Min Act: -0.1700
Data Index: 362183 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.1110. Min Act: -0.1700
Data Index: 7195507 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.1110. Min Act: -0.1700
Data Index: 7528826 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19