Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.3533. Min Act: -0.1700
Data Index: 5425563 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.3533. Min Act: -0.1700
Data Index: 5603299 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.3533. Min Act: -0.1700
Data Index: 6126846 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.3533. Min Act: -0.1700
Data Index: 7515466 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.2908. Min Act: -0.1700
Data Index: 8826443 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.2283. Min Act: -0.1700
Data Index: 2842053 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.1658. Min Act: -0.1700
Data Index: 5126928 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.1970. Min Act: -0.1700
Data Index: 509936 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.1658. Min Act: -0.1700
Data Index: 3835310 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.1345. Min Act: -0.1700
Data Index: 4281470 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.1345. Min Act: -0.1700
Data Index: 8325712 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.1033. Min Act: -0.1700
Data Index: 3805902 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.0720. Min Act: -0.1700
Data Index: 611785 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.0720. Min Act: -0.1700
Data Index: 6261859 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.0408. Min Act: -0.1700
Data Index: 1903874 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.0095. Min Act: -0.1700
Data Index: 5693290 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.0408. Min Act: -0.1700
Data Index: 7157619 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.0408. Min Act: -0.1700
Data Index: 6221472 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.0095. Min Act: -0.1700
Data Index: 323247 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3533. Min Range: -5.3533
Max Act: 5.0095. Min Act: -0.1700
Data Index: 5545190 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19