Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2661 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.4699. Min Act: -0.1700
Data Index: 7041734 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.4074. Min Act: -0.1700
Data Index: 8411965 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.3762. Min Act: -0.1700
Data Index: 6846843 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.3137. Min Act: -0.1700
Data Index: 3610527 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.2512. Min Act: -0.1700
Data Index: 6610201 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.1887. Min Act: -0.1700
Data Index: 4410927 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.1574. Min Act: -0.1700
Data Index: 2884540 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.1262. Min Act: -0.1700
Data Index: 6745308 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.0637. Min Act: -0.1700
Data Index: 4698792 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.0324. Min Act: -0.1700
Data Index: 6886530 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.0324. Min Act: -0.1700
Data Index: 8373059 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.0012. Min Act: -0.1700
Data Index: 7563995 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.0012. Min Act: -0.1700
Data Index: 8294259 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.0012. Min Act: -0.1700
Data Index: 7242807 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4699. Min Range: -6.4699
Max Act: 6.0012. Min Act: -0.1700
Data Index: 4476380 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4699. Min Range: -6.4699
Max Act: 5.9699. Min Act: -0.1700
Data Index: 1792528 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4699. Min Range: -6.4699
Max Act: 5.9699. Min Act: -0.1700
Data Index: 71500 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4699. Min Range: -6.4699
Max Act: 5.9387. Min Act: -0.1700
Data Index: 4541168 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4699. Min Range: -6.4699
Max Act: 5.9387. Min Act: -0.1700
Data Index: 5627528 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4699. Min Range: -6.4699
Max Act: 5.9387. Min Act: -0.1700
Data Index: 3736636 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19