Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2256 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.9637. Min Act: -0.1700
Data Index: 1709070 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.8387. Min Act: -0.1700
Data Index: 7633642 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.4637. Min Act: -0.1700
Data Index: 8652911 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.4012. Min Act: -0.1700
Data Index: 6223975 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.3699. Min Act: -0.1700
Data Index: 7515967 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.3074. Min Act: -0.1700
Data Index: 107995 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.2449. Min Act: -0.1700
Data Index: 4686616 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.2136. Min Act: -0.1700
Data Index: 1784606 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.2136. Min Act: -0.1700
Data Index: 107994 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.1824. Min Act: -0.1700
Data Index: 919249 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.1824. Min Act: -0.1700
Data Index: 2143380 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.1511. Min Act: -0.1700
Data Index: 1675604 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.1511. Min Act: -0.1700
Data Index: 8272934 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.1511. Min Act: -0.1700
Data Index: 3374233 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.1199. Min Act: -0.1700
Data Index: 1050061 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.1199. Min Act: -0.1700
Data Index: 7773383 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.1199. Min Act: -0.1700
Data Index: 6950644 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.1199. Min Act: -0.1700
Data Index: 2888156 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.1199. Min Act: -0.1700
Data Index: 8546881 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9637. Min Range: -4.9637
Max Act: 4.1199. Min Act: -0.1700
Data Index: 4168653 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19