Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3914 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.6125. Min Act: -0.1700
Data Index: 1821282 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.5499. Min Act: -0.1700
Data Index: 3298800 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.4716. Min Act: -0.1700
Data Index: 7898698 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.4716. Min Act: -0.1700
Data Index: 4134358 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.4559. Min Act: -0.1700
Data Index: 5372281 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.4403. Min Act: -0.1700
Data Index: 6508836 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.4246. Min Act: -0.1700
Data Index: 5824895 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.4246. Min Act: -0.1700
Data Index: 4508413 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.4403. Min Act: -0.1700
Data Index: 6044167 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.4089. Min Act: -0.1700
Data Index: 6492505 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.3932. Min Act: -0.1700
Data Index: 830484 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.3775. Min Act: -0.1700
Data Index: 3261512 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.3619. Min Act: -0.1700
Data Index: 5011636 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.3775. Min Act: -0.1700
Data Index: 3992631 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.3462. Min Act: -0.1700
Data Index: 4285235 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.3462. Min Act: -0.1700
Data Index: 1877059 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.3462. Min Act: -0.1700
Data Index: 1956549 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.3462. Min Act: -0.1700
Data Index: 2236273 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.3305. Min Act: -0.1700
Data Index: 1917740 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6125. Min Range: -3.6125
Max Act: 3.3305. Min Act: -0.1700
Data Index: 4645085 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19