Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1914 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4127. Min Range: -5.4127
Max Act: 5.4127. Min Act: -0.1700
Data Index: 4665115 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4127. Min Range: -5.4127
Max Act: 5.1940. Min Act: -0.1700
Data Index: 2406387 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4127. Min Range: -5.4127
Max Act: 5.2252. Min Act: -0.1700
Data Index: 6958016 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4127. Min Range: -5.4127
Max Act: 5.1627. Min Act: -0.1700
Data Index: 8782769 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4127. Min Range: -5.4127
Max Act: 5.1627. Min Act: -0.1700
Data Index: 1964152 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4127. Min Range: -5.4127
Max Act: 5.1002. Min Act: -0.1700
Data Index: 7931278 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4127. Min Range: -5.4127
Max Act: 5.1002. Min Act: -0.1700
Data Index: 5932298 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4127. Min Range: -5.4127
Max Act: 5.0690. Min Act: -0.1700
Data Index: 7038889 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4127. Min Range: -5.4127
Max Act: 5.0690. Min Act: -0.1700
Data Index: 7143079 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4127. Min Range: -5.4127
Max Act: 5.0065. Min Act: -0.1700
Data Index: 632615 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4127. Min Range: -5.4127
Max Act: 5.0065. Min Act: -0.1700
Data Index: 4004377 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4127. Min Range: -5.4127
Max Act: 5.0065. Min Act: -0.1700
Data Index: 5003575 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4127. Min Range: -5.4127
Max Act: 4.9752. Min Act: -0.1700
Data Index: 2431609 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4127. Min Range: -5.4127
Max Act: 4.9440. Min Act: -0.1700
Data Index: 2683914 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4127. Min Range: -5.4127
Max Act: 4.9440. Min Act: -0.1700
Data Index: 5003581 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4127. Min Range: -5.4127
Max Act: 4.9440. Min Act: -0.1700
Data Index: 632614 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4127. Min Range: -5.4127
Max Act: 4.9440. Min Act: -0.1700
Data Index: 6477882 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4127. Min Range: -5.4127
Max Act: 4.9440. Min Act: -0.1700
Data Index: 1836458 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4127. Min Range: -5.4127
Max Act: 4.9752. Min Act: -0.1700
Data Index: 7509915 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4127. Min Range: -5.4127
Max Act: 4.9440. Min Act: -0.1700
Data Index: 7788711 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19