Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1406 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7418. Min Range: -10.7418
Max Act: 10.7418. Min Act: -0.1700
Data Index: 6741119 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7418. Min Range: -10.7418
Max Act: 10.3668. Min Act: -0.1700
Data Index: 5193620 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7418. Min Range: -10.7418
Max Act: 10.3668. Min Act: -0.1700
Data Index: 8809756 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7418. Min Range: -10.7418
Max Act: 10.3043. Min Act: -0.1700
Data Index: 4574074 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7418. Min Range: -10.7418
Max Act: 10.2418. Min Act: -0.1700
Data Index: 6344728 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7418. Min Range: -10.7418
Max Act: 10.2418. Min Act: -0.1700
Data Index: 409808 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7418. Min Range: -10.7418
Max Act: 10.1793. Min Act: -0.1700
Data Index: 5778248 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7418. Min Range: -10.7418
Max Act: 10.1793. Min Act: -0.1700
Data Index: 895928 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7418. Min Range: -10.7418
Max Act: 10.1168. Min Act: -0.1700
Data Index: 836489 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7418. Min Range: -10.7418
Max Act: 10.1168. Min Act: -0.1700
Data Index: 5185631 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7418. Min Range: -10.7418
Max Act: 10.1168. Min Act: -0.1700
Data Index: 4601465 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7418. Min Range: -10.7418
Max Act: 10.0543. Min Act: -0.1700
Data Index: 5114962 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7418. Min Range: -10.7418
Max Act: 9.9918. Min Act: -0.1700
Data Index: 8427245 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7418. Min Range: -10.7418
Max Act: 9.9918. Min Act: -0.1700
Data Index: 2145815 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7418. Min Range: -10.7418
Max Act: 9.9293. Min Act: -0.1700
Data Index: 217665 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7418. Min Range: -10.7418
Max Act: 9.8043. Min Act: -0.1700
Data Index: 4356917 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7418. Min Range: -10.7418
Max Act: 9.8668. Min Act: -0.1700
Data Index: 1904751 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7418. Min Range: -10.7418
Max Act: 9.8668. Min Act: -0.1700
Data Index: 1239102 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7418. Min Range: -10.7418
Max Act: 9.8668. Min Act: -0.1700
Data Index: 6365843 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7418. Min Range: -10.7418
Max Act: 9.8668. Min Act: -0.1700
Data Index: 8071927 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19