Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 651 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.8544. Min Act: -0.1700
Data Index: 85182 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.7919. Min Act: -0.1700
Data Index: 8266812 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.5732. Min Act: -0.1700
Data Index: 7318035 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.4169. Min Act: -0.1700
Data Index: 5756214 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.4169. Min Act: -0.1700
Data Index: 8266798 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.3232. Min Act: -0.1700
Data Index: 522310 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.1982. Min Act: -0.1700
Data Index: 786375 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.2294. Min Act: -0.1700
Data Index: 7059816 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.1982. Min Act: -0.1700
Data Index: 5003592 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.1669. Min Act: -0.1700
Data Index: 7041023 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.1669. Min Act: -0.1700
Data Index: 8266819 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.1357. Min Act: -0.1700
Data Index: 395562 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.1044. Min Act: -0.1700
Data Index: 786373 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.1044. Min Act: -0.1700
Data Index: 5626478 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.1044. Min Act: -0.1700
Data Index: 3018777 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.0732. Min Act: -0.1700
Data Index: 506336 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.0419. Min Act: -0.1700
Data Index: 506339 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.0419. Min Act: -0.1700
Data Index: 506317 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.0419. Min Act: -0.1700
Data Index: 786372 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8544. Min Range: -6.8544
Max Act: 6.0419. Min Act: -0.1700
Data Index: 506318 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19