Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3545 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.1484. Min Act: -0.1700
Data Index: 1635910 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.1484. Min Act: -0.1700
Data Index: 1635887 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.1150. Min Act: -0.1700
Data Index: 1635909 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0983. Min Act: -0.1700
Data Index: 1635908 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0983. Min Act: -0.1700
Data Index: 1635904 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.1150. Min Act: -0.1700
Data Index: 1779989 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0815. Min Act: -0.1700
Data Index: 2425330 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0815. Min Act: -0.1700
Data Index: 1635905 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0815. Min Act: -0.1700
Data Index: 5017830 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0815. Min Act: -0.1700
Data Index: 5976453 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0815. Min Act: -0.1700
Data Index: 2684089 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0815. Min Act: -0.1700
Data Index: 189211 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0647. Min Act: -0.1700
Data Index: 8410542 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0647. Min Act: -0.1700
Data Index: 1933378 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0647. Min Act: -0.1700
Data Index: 8119619 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0815. Min Act: -0.1700
Data Index: 189212 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0647. Min Act: -0.1700
Data Index: 5047187 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0647. Min Act: -0.1700
Data Index: 5976454 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0479. Min Act: -0.1700
Data Index: 6215643 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1484. Min Range: -2.1484
Max Act: 2.0647. Min Act: -0.1700
Data Index: 5280295 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19