Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 910 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0054. Min Range: -8.0054
Max Act: 8.0054. Min Act: -0.1700
Data Index: 5128354 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.3179. Min Act: -0.1700
Data Index: 6647617 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.2242. Min Act: -0.1700
Data Index: 7658310 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.1617. Min Act: -0.1700
Data Index: 4294638 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.1304. Min Act: -0.1700
Data Index: 796905 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.1304. Min Act: -0.1700
Data Index: 2740059 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.0992. Min Act: -0.1700
Data Index: 3691993 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.0679. Min Act: -0.1700
Data Index: 7055691 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.0367. Min Act: -0.1700
Data Index: 4436867 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.0679. Min Act: -0.1700
Data Index: 4425933 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.0367. Min Act: -0.1700
Data Index: 6521387 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.0054. Min Act: -0.1700
Data Index: 2692153 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.0054. Min Act: -0.1700
Data Index: 845852 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0054. Min Range: -8.0054
Max Act: 7.0054. Min Act: -0.1700
Data Index: 5632638 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0054. Min Range: -8.0054
Max Act: 6.9117. Min Act: -0.1700
Data Index: 5347135 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0054. Min Range: -8.0054
Max Act: 6.9429. Min Act: -0.1700
Data Index: 141146 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0054. Min Range: -8.0054
Max Act: 6.9117. Min Act: -0.1700
Data Index: 5760571 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0054. Min Range: -8.0054
Max Act: 6.9117. Min Act: -0.1700
Data Index: 1964974 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0054. Min Range: -8.0054
Max Act: 6.9117. Min Act: -0.1700
Data Index: 6137546 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0054. Min Range: -8.0054
Max Act: 6.9117. Min Act: -0.1700
Data Index: 2268382 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19