Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2762 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.4201. Min Act: -0.1700
Data Index: 6439922 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.2326. Min Act: -0.1700
Data Index: 5121168 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.1388. Min Act: -0.1700
Data Index: 777311 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.1388. Min Act: -0.1700
Data Index: 4522445 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.1076. Min Act: -0.1700
Data Index: 5082615 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.0763. Min Act: -0.1700
Data Index: 777310 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.1076. Min Act: -0.1700
Data Index: 7061587 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.0451. Min Act: -0.1700
Data Index: 6313552 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.0451. Min Act: -0.1700
Data Index: 1883713 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.0451. Min Act: -0.1700
Data Index: 8049900 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.0138. Min Act: -0.1700
Data Index: 1596227 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.0138. Min Act: -0.1700
Data Index: 160330 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4201. Min Range: -5.4201
Max Act: 5.0138. Min Act: -0.1700
Data Index: 6859460 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4201. Min Range: -5.4201
Max Act: 4.9826. Min Act: -0.1700
Data Index: 8104679 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4201. Min Range: -5.4201
Max Act: 4.9826. Min Act: -0.1700
Data Index: 984502 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4201. Min Range: -5.4201
Max Act: 4.9826. Min Act: -0.1700
Data Index: 2025434 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4201. Min Range: -5.4201
Max Act: 4.9513. Min Act: -0.1700
Data Index: 3266617 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4201. Min Range: -5.4201
Max Act: 4.9513. Min Act: -0.1700
Data Index: 7347407 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4201. Min Range: -5.4201
Max Act: 4.9513. Min Act: -0.1700
Data Index: 4691207 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4201. Min Range: -5.4201
Max Act: 4.9513. Min Act: -0.1700
Data Index: 4440887 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19