Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2739 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2359. Min Range: -6.2359
Max Act: 6.2359. Min Act: -0.1700
Data Index: 5804546 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2359. Min Range: -6.2359
Max Act: 6.0484. Min Act: -0.1700
Data Index: 6859931 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2359. Min Range: -6.2359
Max Act: 6.0484. Min Act: -0.1700
Data Index: 1015274 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2359. Min Range: -6.2359
Max Act: 6.0172. Min Act: -0.1700
Data Index: 8042396 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.9859. Min Act: -0.1700
Data Index: 8258624 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.9547. Min Act: -0.1700
Data Index: 333207 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.9234. Min Act: -0.1700
Data Index: 5674883 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.9234. Min Act: -0.1700
Data Index: 5977163 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.8922. Min Act: -0.1700
Data Index: 5833806 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.8609. Min Act: -0.1700
Data Index: 8466755 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.8609. Min Act: -0.1700
Data Index: 3222220 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.8297. Min Act: -0.1700
Data Index: 8620229 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.8297. Min Act: -0.1700
Data Index: 2830349 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.8609. Min Act: -0.1700
Data Index: 3532181 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.8297. Min Act: -0.1684
Data Index: 1828246 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.8297. Min Act: -0.1700
Data Index: 385540 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.7984. Min Act: -0.1700
Data Index: 3532178 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.7672. Min Act: -0.1700
Data Index: 246027 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.7984. Min Act: -0.1700
Data Index: 5585259 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2359. Min Range: -6.2359
Max Act: 5.7984. Min Act: -0.1700
Data Index: 7507060 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19