Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2660 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2913. Min Range: -5.2913
Max Act: 5.2913. Min Act: -0.1700
Data Index: 8360229 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.8538. Min Act: -0.1700
Data Index: 5665280 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.7913. Min Act: -0.1700
Data Index: 5701936 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.7913. Min Act: -0.1700
Data Index: 4436482 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.7288. Min Act: -0.1700
Data Index: 7520984 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.7288. Min Act: -0.1700
Data Index: 5218568 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6976. Min Act: -0.1700
Data Index: 317356 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6976. Min Act: -0.1700
Data Index: 3835817 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6663. Min Act: -0.1700
Data Index: 1358669 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6663. Min Act: -0.1700
Data Index: 24166 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6351. Min Act: -0.1700
Data Index: 6765991 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6351. Min Act: -0.1700
Data Index: 3820466 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6351. Min Act: -0.1700
Data Index: 1878261 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6351. Min Act: -0.1700
Data Index: 8637031 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6351. Min Act: -0.1700
Data Index: 4703053 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6038. Min Act: -0.1700
Data Index: 5021644 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6038. Min Act: -0.1700
Data Index: 7139285 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6038. Min Act: -0.1700
Data Index: 6457002 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.6038. Min Act: -0.1700
Data Index: 3110202 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.5726. Min Act: -0.1700
Data Index: 3133788 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19