Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5083 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.9383. Min Act: -0.1699
Data Index: 841409 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8958. Min Act: -0.1700
Data Index: 7385114 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8958. Min Act: -0.1700
Data Index: 1138129 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8872. Min Act: -0.1700
Data Index: 1520723 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8787. Min Act: -0.1698
Data Index: 4299223 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8616. Min Act: -0.1700
Data Index: 1599017 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8445. Min Act: -0.1700
Data Index: 5460315 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8530. Min Act: -0.1700
Data Index: 5168395 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8445. Min Act: -0.1700
Data Index: 2603996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8359. Min Act: -0.1700
Data Index: 8075080 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8187. Min Act: -0.1699
Data Index: 7326649 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8273. Min Act: -0.1700
Data Index: 8264054 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8273. Min Act: -0.1700
Data Index: 6989876 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8273. Min Act: -0.1700
Data Index: 5807177 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8273. Min Act: -0.1700
Data Index: 1424636 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8187. Min Act: -0.1700
Data Index: 2482825 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8273. Min Act: -0.1700
Data Index: 2272470 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8015. Min Act: -0.1700
Data Index: 597188 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.8015. Min Act: -0.1698
Data Index: 164586 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9383. Min Range: -1.9383
Max Act: 1.7929. Min Act: -0.1700
Data Index: 6205628 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19