Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2423 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.9825. Min Act: -0.1700
Data Index: 869852 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.9825. Min Act: -0.1700
Data Index: 2839836 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.9200. Min Act: -0.1700
Data Index: 1021213 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.8887. Min Act: -0.1700
Data Index: 2849743 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.8575. Min Act: -0.1700
Data Index: 770051 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7950. Min Act: -0.1700
Data Index: 3247189 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7950. Min Act: -0.1700
Data Index: 5614812 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7950. Min Act: -0.1700
Data Index: 3811099 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7637. Min Act: -0.1700
Data Index: 5204296 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7637. Min Act: -0.1700
Data Index: 1331612 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7637. Min Act: -0.1700
Data Index: 1481550 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7637. Min Act: -0.1700
Data Index: 1387507 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7325. Min Act: -0.1700
Data Index: 5783517 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7325. Min Act: -0.1700
Data Index: 7702631 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7325. Min Act: -0.1700
Data Index: 232741 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7325. Min Act: -0.1700
Data Index: 6083354 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7325. Min Act: -0.1700
Data Index: 3234016 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7012. Min Act: -0.1700
Data Index: 6040442 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.6700. Min Act: -0.1700
Data Index: 858535 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9825. Min Range: -5.9825
Max Act: 5.7012. Min Act: -0.1700
Data Index: 6076975 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19