Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 372 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3494. Min Range: -8.3494
Max Act: 8.3494. Min Act: -0.1700
Data Index: 597525 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3494. Min Range: -8.3494
Max Act: 8.2869. Min Act: -0.1700
Data Index: 798922 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3494. Min Range: -8.3494
Max Act: 8.0369. Min Act: -0.1700
Data Index: 5486442 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.9744. Min Act: -0.1700
Data Index: 5392272 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3494. Min Range: -8.3494
Max Act: 8.0369. Min Act: -0.1700
Data Index: 4650614 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.8494. Min Act: -0.1700
Data Index: 8577566 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.7869. Min Act: -0.1700
Data Index: 450622 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.8494. Min Act: -0.1700
Data Index: 5990157 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.7869. Min Act: -0.1700
Data Index: 2897419 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.7869. Min Act: -0.1700
Data Index: 5244378 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.6619. Min Act: -0.1700
Data Index: 5016830 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.5994. Min Act: -0.1700
Data Index: 8509218 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.5994. Min Act: -0.1698
Data Index: 5555168 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.5369. Min Act: -0.1700
Data Index: 6664003 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.4744. Min Act: -0.1700
Data Index: 2027546 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.4744. Min Act: -0.1700
Data Index: 448602 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.4744. Min Act: -0.1700
Data Index: 7666846 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.4744. Min Act: -0.1700
Data Index: 435960 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.4744. Min Act: -0.1700
Data Index: 2200648 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3494. Min Range: -8.3494
Max Act: 7.4744. Min Act: -0.1700
Data Index: 5503865 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19