Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1668 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.5910. Min Act: -0.1700
Data Index: 4378226 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.3722. Min Act: -0.1700
Data Index: 5972255 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2785. Min Act: -0.1700
Data Index: 3047350 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2785. Min Act: -0.1700
Data Index: 4689567 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2472. Min Act: -0.1700
Data Index: 7680038 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2472. Min Act: -0.1700
Data Index: 4261325 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2472. Min Act: -0.1700
Data Index: 2743291 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2160. Min Act: -0.1700
Data Index: 4103209 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2160. Min Act: -0.1700
Data Index: 2071308 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2160. Min Act: -0.1700
Data Index: 8756196 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1535. Min Act: -0.1700
Data Index: 8165816 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1222. Min Act: -0.1700
Data Index: 2993105 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1535. Min Act: -0.1700
Data Index: 778027 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1222. Min Act: -0.1700
Data Index: 2880839 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.0910. Min Act: -0.1700
Data Index: 6731395 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1222. Min Act: -0.1700
Data Index: 6978998 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1222. Min Act: -0.1700
Data Index: 1296790 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1222. Min Act: -0.1700
Data Index: 2670545 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.0910. Min Act: -0.1700
Data Index: 2949010 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.0910. Min Act: -0.1700
Data Index: 1284322 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19