Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2325 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4044. Min Range: -6.4044
Max Act: 6.4044. Min Act: -0.1700
Data Index: 2074927 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4044. Min Range: -6.4044
Max Act: 6.3419. Min Act: -0.1700
Data Index: 8174326 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4044. Min Range: -6.4044
Max Act: 6.2169. Min Act: -0.1700
Data Index: 4020284 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4044. Min Range: -6.4044
Max Act: 6.1231. Min Act: -0.1700
Data Index: 3569554 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4044. Min Range: -6.4044
Max Act: 6.1544. Min Act: -0.1700
Data Index: 6023920 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4044. Min Range: -6.4044
Max Act: 6.0919. Min Act: -0.1700
Data Index: 3390281 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4044. Min Range: -6.4044
Max Act: 6.0294. Min Act: -0.1700
Data Index: 7269895 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4044. Min Range: -6.4044
Max Act: 6.0294. Min Act: -0.1700
Data Index: 7487183 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4044. Min Range: -6.4044
Max Act: 5.9981. Min Act: -0.1700
Data Index: 1114653 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4044. Min Range: -6.4044
Max Act: 5.9981. Min Act: -0.1700
Data Index: 674539 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4044. Min Range: -6.4044
Max Act: 5.9669. Min Act: -0.1700
Data Index: 1481162 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4044. Min Range: -6.4044
Max Act: 5.9669. Min Act: -0.1700
Data Index: 603930 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4044. Min Range: -6.4044
Max Act: 5.9356. Min Act: -0.1700
Data Index: 1800548 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4044. Min Range: -6.4044
Max Act: 5.9044. Min Act: -0.1700
Data Index: 677867 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4044. Min Range: -6.4044
Max Act: 5.9044. Min Act: -0.1700
Data Index: 6751753 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4044. Min Range: -6.4044
Max Act: 5.9356. Min Act: -0.1700
Data Index: 4832192 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4044. Min Range: -6.4044
Max Act: 5.8731. Min Act: -0.1700
Data Index: 842168 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4044. Min Range: -6.4044
Max Act: 5.8731. Min Act: -0.1700
Data Index: 3821293 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4044. Min Range: -6.4044
Max Act: 5.8731. Min Act: -0.1700
Data Index: 5552151 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4044. Min Range: -6.4044
Max Act: 5.8731. Min Act: -0.1700
Data Index: 5736223 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19