Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1680 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.9506. Min Act: -0.1700
Data Index: 355888 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.9336. Min Act: -0.1700
Data Index: 8276885 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.9336. Min Act: -0.1700
Data Index: 4855074 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.9336. Min Act: -0.1700
Data Index: 4085770 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.9166. Min Act: -0.1700
Data Index: 2826124 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.9166. Min Act: -0.1700
Data Index: 6310404 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.9166. Min Act: -0.1700
Data Index: 2526793 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.9166. Min Act: -0.1699
Data Index: 1663434 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.8995. Min Act: -0.1698
Data Index: 6266165 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.8825. Min Act: -0.1700
Data Index: 7694468 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.8825. Min Act: -0.1698
Data Index: 4855070 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.8825. Min Act: -0.1700
Data Index: 7997033 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.8654. Min Act: -0.1700
Data Index: 545535 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.8995. Min Act: -0.1700
Data Index: 2253202 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.8654. Min Act: -0.1700
Data Index: 3696939 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.8654. Min Act: -0.1700
Data Index: 5561677 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.8654. Min Act: -0.1700
Data Index: 335149 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.8654. Min Act: -0.1700
Data Index: 20412 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.8654. Min Act: -0.1700
Data Index: 5441999 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9506. Min Range: -1.9506
Max Act: 1.8654. Min Act: -0.1700
Data Index: 4855073 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19