Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0674. Min Range: -5.0674
Max Act: 5.0674. Min Act: -0.1700
Data Index: 4329478 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.7237. Min Act: -0.1700
Data Index: 1529515 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.6612. Min Act: -0.1700
Data Index: 8396979 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.6612. Min Act: -0.1700
Data Index: 6618038 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.6612. Min Act: -0.1700
Data Index: 6736284 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.6299. Min Act: -0.1700
Data Index: 5360340 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.5674. Min Act: -0.1700
Data Index: 4425399 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.5362. Min Act: -0.1700
Data Index: 2803264 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.5362. Min Act: -0.1700
Data Index: 1299879 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.5049. Min Act: -0.1700
Data Index: 8095052 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.4736. Min Act: -0.1700
Data Index: 5195119 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.4736. Min Act: -0.1700
Data Index: 6154022 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.4736. Min Act: -0.1700
Data Index: 4879002 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.4736. Min Act: -0.1700
Data Index: 4606399 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.4736. Min Act: -0.1700
Data Index: 1813945 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.4424. Min Act: -0.1700
Data Index: 7352691 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.4111. Min Act: -0.1700
Data Index: 5437347 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.4111. Min Act: -0.1700
Data Index: 1457974 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.4111. Min Act: -0.1700
Data Index: 1586398 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0674. Min Range: -5.0674
Max Act: 4.4111. Min Act: -0.1700
Data Index: 2319656 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19