Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4531. Min Range: -8.4531
Max Act: 8.4531. Min Act: -0.1700
Data Index: 466271 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4531. Min Range: -8.4531
Max Act: 8.3906. Min Act: -0.1700
Data Index: 5100250 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4531. Min Range: -8.4531
Max Act: 8.2656. Min Act: -0.1700
Data Index: 4086846 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4531. Min Range: -8.4531
Max Act: 8.0156. Min Act: -0.1700
Data Index: 5389971 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.7656. Min Act: -0.1700
Data Index: 6474807 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.7031. Min Act: -0.1700
Data Index: 457403 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.7031. Min Act: -0.1700
Data Index: 683264 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.6718. Min Act: -0.1700
Data Index: 5003027 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.6718. Min Act: -0.1700
Data Index: 6235233 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.6718. Min Act: -0.1700
Data Index: 254611 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.6406. Min Act: -0.1700
Data Index: 1104127 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.6406. Min Act: -0.1700
Data Index: 2554862 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.6406. Min Act: -0.1700
Data Index: 6671915 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.6406. Min Act: -0.1700
Data Index: 7137755 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.6093. Min Act: -0.1700
Data Index: 4273693 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.5781. Min Act: -0.1700
Data Index: 5466065 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.5781. Min Act: -0.1700
Data Index: 258777 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.5468. Min Act: -0.1700
Data Index: 3643292 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.5468. Min Act: -0.1700
Data Index: 2668257 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4531. Min Range: -8.4531
Max Act: 7.5156. Min Act: -0.1700
Data Index: 434644 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19