Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4789 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4280. Min Range: -5.4280
Max Act: 5.4280. Min Act: -0.1700
Data Index: 2600699 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4280. Min Range: -5.4280
Max Act: 5.3968. Min Act: -0.1700
Data Index: 7398528 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.8968. Min Act: -0.1700
Data Index: 7528805 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.9280. Min Act: -0.1700
Data Index: 4160447 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.8655. Min Act: -0.1700
Data Index: 3724894 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.7718. Min Act: -0.1700
Data Index: 4453562 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.7718. Min Act: -0.1700
Data Index: 2013962 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.7405. Min Act: -0.1700
Data Index: 3656249 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.7405. Min Act: -0.1700
Data Index: 2227980 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.7093. Min Act: -0.1700
Data Index: 7667606 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.7093. Min Act: -0.1700
Data Index: 4912432 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.7093. Min Act: -0.1700
Data Index: 1282714 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.6780. Min Act: -0.1700
Data Index: 3096458 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.5843. Min Act: -0.1700
Data Index: 7435837 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.6155. Min Act: -0.1700
Data Index: 575786 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.5530. Min Act: -0.1700
Data Index: 2792394 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.5530. Min Act: -0.1700
Data Index: 3699449 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.5217. Min Act: -0.1700
Data Index: 4779627 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.5530. Min Act: -0.1700
Data Index: 6310985 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4280. Min Range: -5.4280
Max Act: 4.5530. Min Act: -0.1700
Data Index: 7540830 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19