Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1611 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.9340. Min Act: -0.1700
Data Index: 4518307 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.8090. Min Act: -0.1700
Data Index: 6255343 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.6840. Min Act: -0.1700
Data Index: 928240 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.6840. Min Act: -0.1700
Data Index: 7247288 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.6840. Min Act: -0.1700
Data Index: 4518311 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.6215. Min Act: -0.1700
Data Index: 8785511 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.6215. Min Act: -0.1700
Data Index: 407381 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.5278. Min Act: -0.1700
Data Index: 3463928 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.4653. Min Act: -0.1700
Data Index: 2288244 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.4340. Min Act: -0.1700
Data Index: 6600881 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.4340. Min Act: -0.1700
Data Index: 1531646 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.4028. Min Act: -0.1700
Data Index: 6975243 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.4028. Min Act: -0.1700
Data Index: 5578832 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.4028. Min Act: -0.1700
Data Index: 3914467 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.3715. Min Act: -0.1700
Data Index: 972330 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.4028. Min Act: -0.1700
Data Index: 3070023 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.4028. Min Act: -0.1700
Data Index: 6833977 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.3715. Min Act: -0.1700
Data Index: 2047645 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.3090. Min Act: -0.1700
Data Index: 5114033 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9340. Min Range: -6.9340
Max Act: 6.3403. Min Act: -0.1700
Data Index: 7825686 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19