Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3065 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.7763. Min Act: -0.1700
Data Index: 1023736 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.7138. Min Act: -0.1700
Data Index: 430279 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.6825. Min Act: -0.1700
Data Index: 221144 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.6825. Min Act: -0.1700
Data Index: 8489287 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.6825. Min Act: -0.1700
Data Index: 4311991 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.6200. Min Act: -0.1700
Data Index: 4745485 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.6513. Min Act: -0.1700
Data Index: 3362670 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.6513. Min Act: -0.1700
Data Index: 6949303 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.6513. Min Act: -0.1700
Data Index: 913468 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.6200. Min Act: -0.1700
Data Index: 1721806 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.6200. Min Act: -0.1700
Data Index: 317387 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.6200. Min Act: -0.1700
Data Index: 5641862 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.6200. Min Act: -0.1700
Data Index: 1223247 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.5888. Min Act: -0.1700
Data Index: 8154162 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.5575. Min Act: -0.1700
Data Index: 3293506 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.5575. Min Act: -0.1700
Data Index: 5558483 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.5263. Min Act: -0.1700
Data Index: 6530553 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.5263. Min Act: -0.1700
Data Index: 3678054 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.4950. Min Act: -0.1700
Data Index: 3436749 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7763. Min Range: -6.7763
Max Act: 6.5263. Min Act: -0.1700
Data Index: 2319737 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19