Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.7081. Min Act: -0.1690
Data Index: 6953794 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.7081. Min Act: -0.1697
Data Index: 459530 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.7081. Min Act: -0.1699
Data Index: 6417803 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.7081. Min Act: -0.1699
Data Index: 3839667 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.7241. Min Act: -0.1696
Data Index: 4835938 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.6921. Min Act: -0.1700
Data Index: 74357 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.6600. Min Act: -0.1695
Data Index: 8412040 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.6761. Min Act: -0.1647
Data Index: 3790149 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.6600. Min Act: -0.1700
Data Index: 145204 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.6440. Min Act: -0.1692
Data Index: 7950308 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.6440. Min Act: -0.1700
Data Index: 4900929 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.6279. Min Act: -0.1700
Data Index: 4282307 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.6279. Min Act: -0.1662
Data Index: 480760 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.5797. Min Act: -0.1696
Data Index: 1023089 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.5797. Min Act: -0.1700
Data Index: 8550741 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.5797. Min Act: -0.1700
Data Index: 2370326 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.5797. Min Act: -0.1697
Data Index: 2200100 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.5797. Min Act: -0.1699
Data Index: 863124 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.5474. Min Act: -0.1700
Data Index: 6147305 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7241. Min Range: -2.7241
Max Act: 2.5635. Min Act: -0.1697
Data Index: 837205 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19