Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.2971. Min Act: -0.1700
Data Index: 1297135 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.2476. Min Act: -0.1700
Data Index: 5749037 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.2311. Min Act: -0.1700
Data Index: 7733143 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.2145. Min Act: -0.1700
Data Index: 898 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.2145. Min Act: -0.1700
Data Index: 7133954 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1979. Min Act: -0.1700
Data Index: 849307 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1979. Min Act: -0.1700
Data Index: 1669996 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1813. Min Act: -0.1700
Data Index: 1842441 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1979. Min Act: -0.1700
Data Index: 1866263 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1813. Min Act: -0.1700
Data Index: 1562760 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1647. Min Act: -0.1700
Data Index: 3102754 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1647. Min Act: -0.1700
Data Index: 2782776 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1647. Min Act: -0.1700
Data Index: 7992560 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1813. Min Act: -0.1700
Data Index: 8733868 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1647. Min Act: -0.1700
Data Index: 3863742 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1313. Min Act: -0.1700
Data Index: 3740786 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1647. Min Act: -0.1700
Data Index: 2498094 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1480. Min Act: -0.1700
Data Index: 3767747 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1313. Min Act: -0.1700
Data Index: 259061 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2971. Min Range: -2.2971
Max Act: 2.1480. Min Act: -0.1700
Data Index: 2253921 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19