Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2361 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0385. Min Range: -1.0385
Max Act: 1.0385. Min Act: -0.1695
Data Index: 879756 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0385. Min Range: -1.0385
Max Act: 1.0211. Min Act: -0.1700
Data Index: 7695468 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0385. Min Range: -1.0385
Max Act: 1.0211. Min Act: -0.1700
Data Index: 8705096 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0385. Min Range: -1.0385
Max Act: 1.0124. Min Act: -0.1682
Data Index: 7845745 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0385. Min Range: -1.0385
Max Act: 1.0037. Min Act: -0.1700
Data Index: 7672904 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0385. Min Range: -1.0385
Max Act: 1.0037. Min Act: -0.1700
Data Index: 4232174 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.9777. Min Act: -0.1700
Data Index: 4196041 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.9518. Min Act: -0.1700
Data Index: 8735198 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.9431. Min Act: -0.1686
Data Index: 6428343 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.9431. Min Act: -0.1700
Data Index: 7307674 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.9431. Min Act: -0.1700
Data Index: 6316921 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.8917. Min Act: -0.1700
Data Index: 1828605 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.8917. Min Act: -0.1700
Data Index: 6715152 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.9002. Min Act: -0.1698
Data Index: 3667779 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.8917. Min Act: -0.1700
Data Index: 913004 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.8917. Min Act: -0.1699
Data Index: 6393124 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.8831. Min Act: -0.1698
Data Index: 521045 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.8831. Min Act: -0.1699
Data Index: 2576425 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.8831. Min Act: -0.1700
Data Index: 7292029 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0385. Min Range: -1.0385
Max Act: 0.8661. Min Act: -0.1694
Data Index: 6939524 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19