Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2493 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3869. Min Range: -9.3869
Max Act: 9.3869. Min Act: -0.1700
Data Index: 3501984 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3869. Min Range: -9.3869
Max Act: 9.0119. Min Act: -0.1700
Data Index: 778995 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.9494. Min Act: -0.1700
Data Index: 6589114 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.8869. Min Act: -0.1700
Data Index: 1917648 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.9494. Min Act: -0.1700
Data Index: 932670 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.8869. Min Act: -0.1700
Data Index: 5389976 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.8244. Min Act: -0.1700
Data Index: 3921260 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.8244. Min Act: -0.1700
Data Index: 1420205 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.8244. Min Act: -0.1700
Data Index: 3093506 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.7619. Min Act: -0.1700
Data Index: 7877189 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.8869. Min Act: -0.1700
Data Index: 5763962 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.8244. Min Act: -0.1700
Data Index: 4404437 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.8244. Min Act: -0.1700
Data Index: 2954741 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.8244. Min Act: -0.1700
Data Index: 5777150 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.7619. Min Act: -0.1700
Data Index: 5576997 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.7619. Min Act: -0.1700
Data Index: 3832677 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.7619. Min Act: -0.1700
Data Index: 4586179 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.7619. Min Act: -0.1700
Data Index: 4310696 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.7619. Min Act: -0.1700
Data Index: 5909088 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3869. Min Range: -9.3869
Max Act: 8.6994. Min Act: -0.1700
Data Index: 3893214 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19