Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.9280. Min Act: -0.1700
Data Index: 21608 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.8655. Min Act: -0.1700
Data Index: 8562556 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.8030. Min Act: -0.1700
Data Index: 220988 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.7718. Min Act: -0.1700
Data Index: 5861847 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.7405. Min Act: -0.1700
Data Index: 7563543 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.7405. Min Act: -0.1700
Data Index: 6934606 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.7093. Min Act: -0.1700
Data Index: 909072 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.7093. Min Act: -0.1700
Data Index: 5460225 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.6780. Min Act: -0.1700
Data Index: 7173320 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.6780. Min Act: -0.1700
Data Index: 68230 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.6780. Min Act: -0.1700
Data Index: 461242 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.6780. Min Act: -0.1700
Data Index: 2140699 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.6155. Min Act: -0.1700
Data Index: 4674156 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.6468. Min Act: -0.1700
Data Index: 4906799 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.6468. Min Act: -0.1700
Data Index: 1591334 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.6468. Min Act: -0.1700
Data Index: 3384579 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.6468. Min Act: -0.1700
Data Index: 2691526 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.6155. Min Act: -0.1700
Data Index: 5758130 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.6468. Min Act: -0.1700
Data Index: 469404 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9280. Min Range: -4.9280
Max Act: 4.6155. Min Act: -0.1700
Data Index: 6945129 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19