Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3321 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.5221. Min Act: -0.1700
Data Index: 553931 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.4284. Min Act: -0.1700
Data Index: 7646498 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.4596. Min Act: -0.1700
Data Index: 3259312 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.4284. Min Act: -0.1700
Data Index: 7668765 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.3346. Min Act: -0.1700
Data Index: 3681001 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.3346. Min Act: -0.1700
Data Index: 3274730 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.3659. Min Act: -0.1700
Data Index: 4991664 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.3659. Min Act: -0.1700
Data Index: 2745872 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.3034. Min Act: -0.1700
Data Index: 865070 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.3034. Min Act: -0.1700
Data Index: 3645394 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.3034. Min Act: -0.1700
Data Index: 3201525 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.3034. Min Act: -0.1700
Data Index: 2284750 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.3346. Min Act: -0.1700
Data Index: 679630 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.3346. Min Act: -0.1700
Data Index: 6419627 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.3034. Min Act: -0.1700
Data Index: 4402861 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.2721. Min Act: -0.1699
Data Index: 8803323 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.2721. Min Act: -0.1700
Data Index: 8207930 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.2409. Min Act: -0.1700
Data Index: 5359215 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.2409. Min Act: -0.1700
Data Index: 493159 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5221. Min Range: -5.5221
Max Act: 5.2409. Min Act: -0.1700
Data Index: 5558075 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19