Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3699 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1240. Min Range: -8.1240
Max Act: 8.1240. Min Act: -0.1700
Data Index: 7528030 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.8115. Min Act: -0.1700
Data Index: 1111400 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.8115. Min Act: -0.1700
Data Index: 1274563 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.6240. Min Act: -0.1700
Data Index: 6603239 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.6240. Min Act: -0.1700
Data Index: 4344977 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.5928. Min Act: -0.1700
Data Index: 8304395 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.5615. Min Act: -0.1700
Data Index: 6446315 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.5928. Min Act: -0.1700
Data Index: 7534177 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.5928. Min Act: -0.1700
Data Index: 8412934 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.5615. Min Act: -0.1700
Data Index: 4115672 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.5928. Min Act: -0.1700
Data Index: 7854003 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.5303. Min Act: -0.1700
Data Index: 383079 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.5615. Min Act: -0.1700
Data Index: 4557697 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.5303. Min Act: -0.1700
Data Index: 8620171 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.4990. Min Act: -0.1700
Data Index: 1829331 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.4990. Min Act: -0.1700
Data Index: 2159464 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.5303. Min Act: -0.1700
Data Index: 5210659 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.5303. Min Act: -0.1700
Data Index: 1326636 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.4990. Min Act: -0.1700
Data Index: 2691787 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1240. Min Range: -8.1240
Max Act: 7.4990. Min Act: -0.1700
Data Index: 5901681 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19