Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2891 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.5607. Min Act: -0.1700
Data Index: 4796376 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.4982. Min Act: -0.1700
Data Index: 5256796 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.4045. Min Act: -0.1700
Data Index: 8562850 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.3107. Min Act: -0.1700
Data Index: 8781919 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.2170. Min Act: -0.1700
Data Index: 4716578 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.2170. Min Act: -0.1700
Data Index: 5429297 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.1857. Min Act: -0.1700
Data Index: 8150476 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.1232. Min Act: -0.1700
Data Index: 3756335 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.0920. Min Act: -0.1700
Data Index: 410332 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.0295. Min Act: -0.1700
Data Index: 435980 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.0295. Min Act: -0.1700
Data Index: 5154014 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9670. Min Act: -0.1700
Data Index: 4507209 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9982. Min Act: -0.1700
Data Index: 465173 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9982. Min Act: -0.1700
Data Index: 8282757 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9670. Min Act: -0.1700
Data Index: 1333029 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9982. Min Act: -0.1700
Data Index: 6222825 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9357. Min Act: -0.1700
Data Index: 2561572 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9357. Min Act: -0.1700
Data Index: 6912716 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9357. Min Act: -0.1700
Data Index: 864839 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9357. Min Act: -0.1700
Data Index: 8232008 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19