Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7892. Min Range: -7.7892
Max Act: 7.7892. Min Act: -0.1700
Data Index: 7779551 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7892. Min Range: -7.7892
Max Act: 7.4454. Min Act: -0.1700
Data Index: 7113497 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7892. Min Range: -7.7892
Max Act: 7.4142. Min Act: -0.1700
Data Index: 2696587 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7892. Min Range: -7.7892
Max Act: 7.2267. Min Act: -0.1700
Data Index: 7274026 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7892. Min Range: -7.7892
Max Act: 7.1329. Min Act: -0.1700
Data Index: 7885797 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7892. Min Range: -7.7892
Max Act: 7.1329. Min Act: -0.1700
Data Index: 4885141 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7892. Min Range: -7.7892
Max Act: 7.1017. Min Act: -0.1700
Data Index: 4690758 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7892. Min Range: -7.7892
Max Act: 7.0392. Min Act: -0.1700
Data Index: 1341617 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7892. Min Range: -7.7892
Max Act: 7.0079. Min Act: -0.1700
Data Index: 5169365 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7892. Min Range: -7.7892
Max Act: 6.9767. Min Act: -0.1700
Data Index: 3223408 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7892. Min Range: -7.7892
Max Act: 6.9454. Min Act: -0.1700
Data Index: 5692548 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7892. Min Range: -7.7892
Max Act: 6.9454. Min Act: -0.1700
Data Index: 3360092 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7892. Min Range: -7.7892
Max Act: 6.9454. Min Act: -0.1700
Data Index: 4397864 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7892. Min Range: -7.7892
Max Act: 6.9142. Min Act: -0.1700
Data Index: 4173697 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7892. Min Range: -7.7892
Max Act: 6.8829. Min Act: -0.1700
Data Index: 6780415 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7892. Min Range: -7.7892
Max Act: 6.9142. Min Act: -0.1700
Data Index: 7408343 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7892. Min Range: -7.7892
Max Act: 6.8517. Min Act: -0.1700
Data Index: 5176815 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7892. Min Range: -7.7892
Max Act: 6.8829. Min Act: -0.1700
Data Index: 2181542 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7892. Min Range: -7.7892
Max Act: 6.8517. Min Act: -0.1700
Data Index: 4503609 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7892. Min Range: -7.7892
Max Act: 6.9142. Min Act: -0.1700
Data Index: 4812060 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19