Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.5170. Min Act: -0.1700
Data Index: 8229490 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.4545. Min Act: -0.1700
Data Index: 4763726 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.4545. Min Act: -0.1700
Data Index: 6845435 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.4545. Min Act: -0.1700
Data Index: 8375394 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.3920. Min Act: -0.1700
Data Index: 1399749 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.3920. Min Act: -0.1700
Data Index: 4893929 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.3920. Min Act: -0.1700
Data Index: 5081482 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.3920. Min Act: -0.1700
Data Index: 362704 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.2670. Min Act: -0.1700
Data Index: 6539193 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.2670. Min Act: -0.1700
Data Index: 4856514 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.2670. Min Act: -0.1700
Data Index: 5593310 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.2670. Min Act: -0.1700
Data Index: 5614685 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.2670. Min Act: -0.1700
Data Index: 4222612 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.2045. Min Act: -0.1700
Data Index: 1369014 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.1420. Min Act: -0.1700
Data Index: 3152368 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.2045. Min Act: -0.1700
Data Index: 5784115 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.2045. Min Act: -0.1700
Data Index: 1240697 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.2045. Min Act: -0.1700
Data Index: 8096273 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.2045. Min Act: -0.1700
Data Index: 7087190 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5170. Min Range: -8.5170
Max Act: 8.2045. Min Act: -0.1700
Data Index: 5904503 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19