Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6322 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0109. Min Range: -7.0109
Max Act: 7.0109. Min Act: -0.1700
Data Index: 3798251 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0109. Min Range: -7.0109
Max Act: 7.0109. Min Act: -0.1700
Data Index: 2108082 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.9172. Min Act: -0.1700
Data Index: 3976261 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.9172. Min Act: -0.1700
Data Index: 463670 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.8547. Min Act: -0.1700
Data Index: 7942972 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.8547. Min Act: -0.1700
Data Index: 2173574 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.8859. Min Act: -0.1700
Data Index: 281002 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.8547. Min Act: -0.1700
Data Index: 7530238 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.8234. Min Act: -0.1700
Data Index: 786393 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.7922. Min Act: -0.1700
Data Index: 5391042 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.7922. Min Act: -0.1700
Data Index: 1230737 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.7609. Min Act: -0.1700
Data Index: 3170412 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.7297. Min Act: -0.1700
Data Index: 3118859 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.7297. Min Act: -0.1700
Data Index: 5753771 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.6984. Min Act: -0.1700
Data Index: 1871527 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.6984. Min Act: -0.1700
Data Index: 7183836 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.6984. Min Act: -0.1700
Data Index: 331960 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.6984. Min Act: -0.1700
Data Index: 1926893 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.6672. Min Act: -0.1700
Data Index: 5423205 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.6672. Min Act: -0.1700
Data Index: 2143219 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19