Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5835 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1235. Min Range: -5.1235
Max Act: 5.1235. Min Act: -0.1700
Data Index: 681942 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1235. Min Range: -5.1235
Max Act: 5.0297. Min Act: -0.1700
Data Index: 1024340 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9672. Min Act: -0.1700
Data Index: 6828564 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.8110. Min Act: -0.1700
Data Index: 5150176 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.7797. Min Act: -0.1700
Data Index: 8004519 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.7797. Min Act: -0.1700
Data Index: 1644045 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.7485. Min Act: -0.1700
Data Index: 6729987 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.7485. Min Act: -0.1700
Data Index: 4362923 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.7172. Min Act: -0.1700
Data Index: 5049190 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.7172. Min Act: -0.1700
Data Index: 1946923 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.6860. Min Act: -0.1700
Data Index: 3407454 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.7485. Min Act: -0.1700
Data Index: 1944370 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.7172. Min Act: -0.1700
Data Index: 3326130 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.7485. Min Act: -0.1700
Data Index: 5609789 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.7172. Min Act: -0.1700
Data Index: 8462780 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.6860. Min Act: -0.1700
Data Index: 2118020 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.6860. Min Act: -0.1700
Data Index: 6587726 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.6860. Min Act: -0.1700
Data Index: 4129951 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.7172. Min Act: -0.1700
Data Index: 2074936 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.6860. Min Act: -0.1700
Data Index: 1239110 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19