Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5617 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.8083. Min Act: -0.1700
Data Index: 2787662 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.7458. Min Act: -0.1700
Data Index: 2628500 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.7146. Min Act: -0.1700
Data Index: 2181896 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.6521. Min Act: -0.1700
Data Index: 7376988 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.6208. Min Act: -0.1700
Data Index: 6116296 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.5896. Min Act: -0.1700
Data Index: 1528665 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.5896. Min Act: -0.1700
Data Index: 8160304 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.5896. Min Act: -0.1700
Data Index: 1123257 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.5271. Min Act: -0.1700
Data Index: 2229401 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.5271. Min Act: -0.1700
Data Index: 2209 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.5271. Min Act: -0.1700
Data Index: 564853 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.5271. Min Act: -0.1700
Data Index: 6712496 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.5271. Min Act: -0.1700
Data Index: 2716317 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.5271. Min Act: -0.1700
Data Index: 4542158 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.4958. Min Act: -0.1700
Data Index: 4563388 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.4646. Min Act: -0.1700
Data Index: 4861571 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.4646. Min Act: -0.1700
Data Index: 6484126 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.4646. Min Act: -0.1700
Data Index: 2628498 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.4646. Min Act: -0.1700
Data Index: 2631619 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8083. Min Range: -5.8083
Max Act: 5.4646. Min Act: -0.1700
Data Index: 457825 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19