Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2507 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2215. Min Range: -6.2215
Max Act: 6.2215. Min Act: -0.1700
Data Index: 421582 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2215. Min Range: -6.2215
Max Act: 6.1903. Min Act: -0.1700
Data Index: 6719592 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2215. Min Range: -6.2215
Max Act: 6.0653. Min Act: -0.1700
Data Index: 54877 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2215. Min Range: -6.2215
Max Act: 6.0028. Min Act: -0.1700
Data Index: 2104493 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.9715. Min Act: -0.1700
Data Index: 4750312 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.9403. Min Act: -0.1700
Data Index: 4859762 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.9403. Min Act: -0.1700
Data Index: 5842216 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.9090. Min Act: -0.1700
Data Index: 7480883 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.8778. Min Act: -0.1700
Data Index: 2014711 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.8778. Min Act: -0.1700
Data Index: 477846 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.8778. Min Act: -0.1700
Data Index: 7945628 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.8778. Min Act: -0.1700
Data Index: 2385337 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.8465. Min Act: -0.1700
Data Index: 3592731 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.8465. Min Act: -0.1700
Data Index: 2872300 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.8465. Min Act: -0.1700
Data Index: 3787717 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.8153. Min Act: -0.1700
Data Index: 3998085 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.8153. Min Act: -0.1700
Data Index: 4884275 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.8153. Min Act: -0.1700
Data Index: 2768031 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.8153. Min Act: -0.1700
Data Index: 3622979 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2215. Min Range: -6.2215
Max Act: 5.8153. Min Act: -0.1700
Data Index: 3659950 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19