Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2489 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1495. Min Range: -6.1495
Max Act: 6.1495. Min Act: -0.1700
Data Index: 7387164 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.9932. Min Act: -0.1700
Data Index: 3434572 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.9620. Min Act: -0.1700
Data Index: 4979364 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.9932. Min Act: -0.1700
Data Index: 4391750 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.8995. Min Act: -0.1700
Data Index: 1289905 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.8995. Min Act: -0.1700
Data Index: 2727184 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.8995. Min Act: -0.1700
Data Index: 1425838 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.8682. Min Act: -0.1700
Data Index: 701585 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.8370. Min Act: -0.1700
Data Index: 3710282 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7745. Min Act: -0.1700
Data Index: 4318131 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.8057. Min Act: -0.1700
Data Index: 2090923 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7432. Min Act: -0.1700
Data Index: 107533 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7432. Min Act: -0.1700
Data Index: 2024473 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7120. Min Act: -0.1700
Data Index: 6269918 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7120. Min Act: -0.1700
Data Index: 5902455 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7432. Min Act: -0.1700
Data Index: 3677917 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.6807. Min Act: -0.1700
Data Index: 5554697 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.6807. Min Act: -0.1700
Data Index: 5745916 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.6495. Min Act: -0.1700
Data Index: 7096046 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.6182. Min Act: -0.1700
Data Index: 6577437 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19