Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.7648. Min Act: -0.1700
Data Index: 4301559 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.7648. Min Act: -0.1700
Data Index: 6962231 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.7335. Min Act: -0.1700
Data Index: 3585221 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.7023. Min Act: -0.1700
Data Index: 6171710 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.6398. Min Act: -0.1700
Data Index: 3751076 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.6710. Min Act: -0.1700
Data Index: 1108273 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.6398. Min Act: -0.1700
Data Index: 4242648 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.6085. Min Act: -0.1700
Data Index: 3952243 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.5460. Min Act: -0.1700
Data Index: 8168019 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.6085. Min Act: -0.1700
Data Index: 333624 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.5773. Min Act: -0.1700
Data Index: 3071396 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.5460. Min Act: -0.1700
Data Index: 1320286 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.5773. Min Act: -0.1700
Data Index: 2938567 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.5460. Min Act: -0.1700
Data Index: 792809 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.5460. Min Act: -0.1700
Data Index: 7608920 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.5148. Min Act: -0.1700
Data Index: 4111534 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.5148. Min Act: -0.1700
Data Index: 6122200 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.4835. Min Act: -0.1700
Data Index: 7786127 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.4835. Min Act: -0.1700
Data Index: 6622123 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7648. Min Range: -4.7648
Max Act: 4.4522. Min Act: -0.1700
Data Index: 3141267 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19