Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1831 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.2669. Min Act: -0.1692
Data Index: 3799153 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.2826. Min Act: -0.1700
Data Index: 8654379 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.2511. Min Act: -0.1700
Data Index: 8392642 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.2511. Min Act: -0.1700
Data Index: 8576132 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.2354. Min Act: -0.1697
Data Index: 985941 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.2040. Min Act: -0.1700
Data Index: 8358283 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.2197. Min Act: -0.1700
Data Index: 6947463 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1725. Min Act: -0.1700
Data Index: 5297053 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1883. Min Act: -0.1700
Data Index: 2434757 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1725. Min Act: -0.1676
Data Index: 1818859 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1883. Min Act: -0.1700
Data Index: 5729912 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1568. Min Act: -0.1697
Data Index: 4238710 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1568. Min Act: -0.1700
Data Index: 3492487 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1411. Min Act: -0.1699
Data Index: 8826021 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1411. Min Act: -0.1700
Data Index: 6792322 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1095. Min Act: -0.1696
Data Index: 3137592 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1411. Min Act: -0.1700
Data Index: 1858394 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1411. Min Act: -0.1700
Data Index: 8816364 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1253. Min Act: -0.1700
Data Index: 8376176 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2826. Min Range: -3.2826
Max Act: 3.1411. Min Act: -0.1680
Data Index: 7929139 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19