Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6156 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.5970. Min Act: -0.1700
Data Index: 4636198 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.3158. Min Act: -0.1700
Data Index: 6153247 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.2845. Min Act: -0.1700
Data Index: 5068530 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.2220. Min Act: -0.1700
Data Index: 3426140 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.1908. Min Act: -0.1700
Data Index: 4394165 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.2220. Min Act: -0.1700
Data Index: 3255451 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.1595. Min Act: -0.1700
Data Index: 6059320 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.1595. Min Act: -0.1700
Data Index: 5162825 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.1283. Min Act: -0.1700
Data Index: 2105046 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.0970. Min Act: -0.1700
Data Index: 2788973 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.0970. Min Act: -0.1700
Data Index: 4624887 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.0658. Min Act: -0.1700
Data Index: 1274331 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.0658. Min Act: -0.1700
Data Index: 5098603 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.0658. Min Act: -0.1700
Data Index: 8261129 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.0658. Min Act: -0.1700
Data Index: 7921275 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.0345. Min Act: -0.1700
Data Index: 2105085 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.0345. Min Act: -0.1700
Data Index: 8438948 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.0345. Min Act: -0.1700
Data Index: 8044621 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.0345. Min Act: -0.1700
Data Index: 413229 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5970. Min Range: -5.5970
Max Act: 5.0345. Min Act: -0.1700
Data Index: 1902662 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19