Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2961 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.5423. Min Act: -0.1700
Data Index: 4005648 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.5111. Min Act: -0.1700
Data Index: 6438682 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.4486. Min Act: -0.1700
Data Index: 5862535 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.3861. Min Act: -0.1700
Data Index: 7502384 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.3548. Min Act: -0.1700
Data Index: 5115638 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.3236. Min Act: -0.1700
Data Index: 4722327 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.2298. Min Act: -0.1700
Data Index: 6795978 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.1986. Min Act: -0.1700
Data Index: 7767421 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.1986. Min Act: -0.1700
Data Index: 6142166 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.1673. Min Act: -0.1700
Data Index: 6348985 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.1361. Min Act: -0.1700
Data Index: 422320 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.0735. Min Act: -0.1700
Data Index: 4741631 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.0735. Min Act: -0.1700
Data Index: 7516771 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.0423. Min Act: -0.1700
Data Index: 2332692 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.0110. Min Act: -0.1700
Data Index: 6391025 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.0110. Min Act: -0.1700
Data Index: 120479 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.0110. Min Act: -0.1700
Data Index: 4356379 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.0110. Min Act: -0.1700
Data Index: 1435574 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.0423. Min Act: -0.1700
Data Index: 4025694 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5423. Min Range: -4.5423
Max Act: 4.0110. Min Act: -0.1700
Data Index: 8095199 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19