Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4746 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3442. Min Range: -2.3442
Max Act: 2.3442. Min Act: -0.1700
Data Index: 2994101 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3442. Min Range: -2.3442
Max Act: 2.0454. Min Act: -0.1700
Data Index: 33479 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3442. Min Range: -2.3442
Max Act: 2.0454. Min Act: -0.1700
Data Index: 3168675 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.9863. Min Act: -0.1700
Data Index: 7516920 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.9694. Min Act: -0.1699
Data Index: 6442791 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.9524. Min Act: -0.1700
Data Index: 1353445 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.9524. Min Act: -0.1698
Data Index: 8137253 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.9439. Min Act: -0.1700
Data Index: 3964191 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.9354. Min Act: -0.1700
Data Index: 2994105 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.9184. Min Act: -0.1700
Data Index: 7246646 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.8928. Min Act: -0.1700
Data Index: 7678327 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.8843. Min Act: -0.1700
Data Index: 2119174 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.8843. Min Act: -0.1700
Data Index: 5702515 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.8672. Min Act: -0.1700
Data Index: 5780404 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.8758. Min Act: -0.1700
Data Index: 6871885 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.8501. Min Act: -0.1700
Data Index: 670318 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.8415. Min Act: -0.1700
Data Index: 8119319 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.8501. Min Act: -0.1700
Data Index: 272732 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.8415. Min Act: -0.1700
Data Index: 1058800 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3442. Min Range: -2.3442
Max Act: 1.8329. Min Act: -0.1700
Data Index: 3225596 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19