Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1356 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0548. Min Range: -6.0548
Max Act: 6.0548. Min Act: -0.1700
Data Index: 6362603 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.8673. Min Act: -0.1700
Data Index: 8693772 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.8673. Min Act: -0.1700
Data Index: 3329025 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.8048. Min Act: -0.1700
Data Index: 7594776 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.8048. Min Act: -0.1700
Data Index: 4167550 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.8048. Min Act: -0.1700
Data Index: 7135453 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.7423. Min Act: -0.1700
Data Index: 7426856 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.7423. Min Act: -0.1700
Data Index: 2091958 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.7111. Min Act: -0.1700
Data Index: 838181 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.7111. Min Act: -0.1700
Data Index: 644529 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.6798. Min Act: -0.1700
Data Index: 7428102 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.7111. Min Act: -0.1700
Data Index: 1832634 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.6798. Min Act: -0.1700
Data Index: 245542 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.6798. Min Act: -0.1700
Data Index: 7429959 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.6798. Min Act: -0.1700
Data Index: 4890734 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.6798. Min Act: -0.1700
Data Index: 7879674 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.6798. Min Act: -0.1700
Data Index: 3178339 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.6798. Min Act: -0.1700
Data Index: 7608450 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.6486. Min Act: -0.1700
Data Index: 6315270 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0548. Min Range: -6.0548
Max Act: 5.6486. Min Act: -0.1700
Data Index: 498809 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19