Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2229 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.4807. Min Act: -0.1700
Data Index: 2187396 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.3867. Min Act: -0.1700
Data Index: 7611423 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.2925. Min Act: -0.1700
Data Index: 639484 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.2768. Min Act: -0.1700
Data Index: 6218810 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.2454. Min Act: -0.1700
Data Index: 5800595 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.2297. Min Act: -0.1700
Data Index: 1632303 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.1983. Min Act: -0.1700
Data Index: 4448876 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.1983. Min Act: -0.1700
Data Index: 1428971 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.1668. Min Act: -0.1700
Data Index: 8629783 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.1668. Min Act: -0.1700
Data Index: 232785 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.1668. Min Act: -0.1700
Data Index: 141890 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.1353. Min Act: -0.1700
Data Index: 5762472 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.1511. Min Act: -0.1700
Data Index: 1143131 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.1196. Min Act: -0.1700
Data Index: 5134233 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.1196. Min Act: -0.1700
Data Index: 6344654 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.1038. Min Act: -0.1700
Data Index: 349253 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.1038. Min Act: -0.1700
Data Index: 8058848 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.0880. Min Act: -0.1700
Data Index: 5179641 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.1038. Min Act: -0.1700
Data Index: 302306 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4807. Min Range: -3.4807
Max Act: 3.0723. Min Act: -0.1700
Data Index: 136030 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19