Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6079 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8013. Min Range: -7.8013
Max Act: 7.8013. Min Act: -0.1700
Data Index: 8003935 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8013. Min Range: -7.8013
Max Act: 7.2701. Min Act: -0.1700
Data Index: 171934 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8013. Min Range: -7.8013
Max Act: 7.1451. Min Act: -0.1700
Data Index: 8019343 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8013. Min Range: -7.8013
Max Act: 7.1451. Min Act: -0.1700
Data Index: 5913881 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8013. Min Range: -7.8013
Max Act: 7.0201. Min Act: -0.1700
Data Index: 8600965 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.9888. Min Act: -0.1700
Data Index: 7668037 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.9576. Min Act: -0.1700
Data Index: 1900579 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.9576. Min Act: -0.1700
Data Index: 3253640 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.9576. Min Act: -0.1700
Data Index: 412454 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.9263. Min Act: -0.1700
Data Index: 2328776 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.9576. Min Act: -0.1700
Data Index: 5088212 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.9263. Min Act: -0.1700
Data Index: 2688484 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.8638. Min Act: -0.1700
Data Index: 6178491 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.8638. Min Act: -0.1700
Data Index: 18834 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.8326. Min Act: -0.1700
Data Index: 2329639 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.8013. Min Act: -0.1700
Data Index: 6899492 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.7701. Min Act: -0.1700
Data Index: 5434124 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.8013. Min Act: -0.1700
Data Index: 1275329 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.8013. Min Act: -0.1700
Data Index: 4169557 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8013. Min Range: -7.8013
Max Act: 6.8013. Min Act: -0.1700
Data Index: 5644543 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19