Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.8112. Min Act: -0.1700
Data Index: 1403638 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.8112. Min Act: -0.1700
Data Index: 5784815 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.5612. Min Act: -0.1700
Data Index: 5428328 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.4675. Min Act: -0.1700
Data Index: 3164549 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.4362. Min Act: -0.1700
Data Index: 4600041 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.3112. Min Act: -0.1700
Data Index: 4589569 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.3112. Min Act: -0.1700
Data Index: 4388996 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.3425. Min Act: -0.1700
Data Index: 4609359 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.2487. Min Act: -0.1700
Data Index: 835852 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.2487. Min Act: -0.1700
Data Index: 7228092 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.2175. Min Act: -0.1700
Data Index: 7591623 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.1862. Min Act: -0.1700
Data Index: 4374363 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.1862. Min Act: -0.1700
Data Index: 7662133 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.1862. Min Act: -0.1700
Data Index: 4873907 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.1237. Min Act: -0.1700
Data Index: 7656824 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8112. Min Range: -6.8112
Max Act: 6.0925. Min Act: -0.1700
Data Index: 6665551 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8112. Min Range: -6.8112
Max Act: 5.9987. Min Act: -0.1700
Data Index: 2762193 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8112. Min Range: -6.8112
Max Act: 5.9987. Min Act: -0.1700
Data Index: 2923543 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8112. Min Range: -6.8112
Max Act: 5.9987. Min Act: -0.1700
Data Index: 7031438 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8112. Min Range: -6.8112
Max Act: 5.9987. Min Act: -0.1700
Data Index: 8179435 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19