Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2154 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7089. Min Range: -10.7089
Max Act: 10.7089. Min Act: -0.1700
Data Index: 5959211 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7089. Min Range: -10.7089
Max Act: 10.3339. Min Act: -0.1700
Data Index: 1053372 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7089. Min Range: -10.7089
Max Act: 10.1464. Min Act: -0.1700
Data Index: 8020568 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7089. Min Range: -10.7089
Max Act: 10.0839. Min Act: -0.1700
Data Index: 6594495 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7089. Min Range: -10.7089
Max Act: 10.0214. Min Act: -0.1700
Data Index: 4676468 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.9589. Min Act: -0.1700
Data Index: 4529910 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.9589. Min Act: -0.1700
Data Index: 7700159 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.8964. Min Act: -0.1700
Data Index: 1825187 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.7714. Min Act: -0.1700
Data Index: 6670615 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.7714. Min Act: -0.1700
Data Index: 370598 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.7714. Min Act: -0.1700
Data Index: 7115745 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.6464. Min Act: -0.1700
Data Index: 7455313 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.6464. Min Act: -0.1700
Data Index: 4806408 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.5839. Min Act: -0.1700
Data Index: 171059 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.5839. Min Act: -0.1700
Data Index: 5946516 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.5839. Min Act: -0.1700
Data Index: 318325 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.5839. Min Act: -0.1700
Data Index: 242462 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.5214. Min Act: -0.1700
Data Index: 5965273 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.5214. Min Act: -0.1700
Data Index: 813215 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7089. Min Range: -10.7089
Max Act: 9.5214. Min Act: -0.1700
Data Index: 4021742 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19