Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 146 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1482. Min Range: -6.1482
Max Act: 6.1482. Min Act: -0.1700
Data Index: 5821627 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1482. Min Range: -6.1482
Max Act: 6.0857. Min Act: -0.1700
Data Index: 950118 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1482. Min Range: -6.1482
Max Act: 6.0857. Min Act: -0.1700
Data Index: 8249914 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.9920. Min Act: -0.1700
Data Index: 2339822 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1482. Min Range: -6.1482
Max Act: 6.0232. Min Act: -0.1700
Data Index: 7498353 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.9920. Min Act: -0.1700
Data Index: 678126 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.9607. Min Act: -0.1700
Data Index: 5943391 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.8982. Min Act: -0.1700
Data Index: 2791927 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.9607. Min Act: -0.1700
Data Index: 6163480 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.8982. Min Act: -0.1700
Data Index: 2840688 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.8670. Min Act: -0.1700
Data Index: 1739757 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.8982. Min Act: -0.1700
Data Index: 6052026 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.8982. Min Act: -0.1700
Data Index: 541285 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.8357. Min Act: -0.1700
Data Index: 677330 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.8357. Min Act: -0.1700
Data Index: 2976258 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.8357. Min Act: -0.1700
Data Index: 914938 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.8045. Min Act: -0.1700
Data Index: 7845072 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.7732. Min Act: -0.1700
Data Index: 8405817 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.7732. Min Act: -0.1700
Data Index: 5081730 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1482. Min Range: -6.1482
Max Act: 5.7732. Min Act: -0.1700
Data Index: 7914090 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19