Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4437 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.6708. Min Act: -0.1700
Data Index: 2140908 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.5770. Min Act: -0.1700
Data Index: 1738736 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.4520. Min Act: -0.1700
Data Index: 6412013 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.4208. Min Act: -0.1700
Data Index: 278463 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.4208. Min Act: -0.1700
Data Index: 5776657 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.3270. Min Act: -0.1700
Data Index: 2756117 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.2020. Min Act: -0.1700
Data Index: 6379799 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.1708. Min Act: -0.1700
Data Index: 1183190 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.1708. Min Act: -0.1700
Data Index: 4856215 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.1083. Min Act: -0.1700
Data Index: 2962378 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.1083. Min Act: -0.1700
Data Index: 3279718 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.1083. Min Act: -0.1700
Data Index: 1702617 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.1395. Min Act: -0.1700
Data Index: 661056 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.0770. Min Act: -0.1700
Data Index: 8217944 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.0458. Min Act: -0.1700
Data Index: 8269120 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.0145. Min Act: -0.1700
Data Index: 3727257 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.0145. Min Act: -0.1700
Data Index: 7409341 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.0145. Min Act: -0.1700
Data Index: 423953 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.0145. Min Act: -0.1700
Data Index: 2555318 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6708. Min Range: -5.6708
Max Act: 5.0145. Min Act: -0.1700
Data Index: 2945311 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19