Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5793 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.8026. Min Act: -0.1700
Data Index: 4715812 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.8026. Min Act: -0.1700
Data Index: 7191194 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.6776. Min Act: -0.1700
Data Index: 2488912 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.6776. Min Act: -0.1700
Data Index: 2287473 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.4901. Min Act: -0.1700
Data Index: 2609432 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.4589. Min Act: -0.1700
Data Index: 4192378 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.4589. Min Act: -0.1700
Data Index: 949857 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.4589. Min Act: -0.1700
Data Index: 7368233 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.2714. Min Act: -0.1700
Data Index: 5586752 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.3026. Min Act: -0.1700
Data Index: 8714513 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.2089. Min Act: -0.1700
Data Index: 6485509 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.1776. Min Act: -0.1700
Data Index: 359118 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.1776. Min Act: -0.1700
Data Index: 1503081 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.1776. Min Act: -0.1700
Data Index: 205175 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.1464. Min Act: -0.1700
Data Index: 4401166 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.1151. Min Act: -0.1700
Data Index: 1714709 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.0839. Min Act: -0.1700
Data Index: 1550840 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.0526. Min Act: -0.1700
Data Index: 7998533 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8026. Min Range: -7.8026
Max Act: 7.0214. Min Act: -0.1700
Data Index: 7101937 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8026. Min Range: -7.8026
Max Act: 6.9901. Min Act: -0.1700
Data Index: 742581 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19