Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3786 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3883. Min Range: -5.3883
Max Act: 5.3883. Min Act: -0.1700
Data Index: 4772373 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3883. Min Range: -5.3883
Max Act: 5.2633. Min Act: -0.1700
Data Index: 2747647 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3883. Min Range: -5.3883
Max Act: 5.1696. Min Act: -0.1700
Data Index: 2702810 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3883. Min Range: -5.3883
Max Act: 5.1696. Min Act: -0.1700
Data Index: 4497910 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3883. Min Range: -5.3883
Max Act: 5.1696. Min Act: -0.1700
Data Index: 3660724 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3883. Min Range: -5.3883
Max Act: 5.0758. Min Act: -0.1700
Data Index: 4390465 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3883. Min Range: -5.3883
Max Act: 5.0446. Min Act: -0.1700
Data Index: 7299250 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3883. Min Range: -5.3883
Max Act: 5.0133. Min Act: -0.1700
Data Index: 1565137 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3883. Min Range: -5.3883
Max Act: 5.0446. Min Act: -0.1700
Data Index: 7046528 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3883. Min Range: -5.3883
Max Act: 5.0446. Min Act: -0.1700
Data Index: 4127231 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3883. Min Range: -5.3883
Max Act: 4.9821. Min Act: -0.1700
Data Index: 8788042 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3883. Min Range: -5.3883
Max Act: 4.9821. Min Act: -0.1700
Data Index: 5300994 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3883. Min Range: -5.3883
Max Act: 4.9508. Min Act: -0.1700
Data Index: 313969 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3883. Min Range: -5.3883
Max Act: 4.9821. Min Act: -0.1700
Data Index: 6224868 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3883. Min Range: -5.3883
Max Act: 4.9508. Min Act: -0.1700
Data Index: 2156406 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3883. Min Range: -5.3883
Max Act: 4.9508. Min Act: -0.1700
Data Index: 8779867 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3883. Min Range: -5.3883
Max Act: 4.9508. Min Act: -0.1700
Data Index: 1675573 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3883. Min Range: -5.3883
Max Act: 4.8883. Min Act: -0.1700
Data Index: 1127069 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3883. Min Range: -5.3883
Max Act: 4.9196. Min Act: -0.1700
Data Index: 92563 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3883. Min Range: -5.3883
Max Act: 4.8883. Min Act: -0.1700
Data Index: 2514393 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19