Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4349 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.3470. Min Range: -10.3470
Max Act: 10.3470. Min Act: -0.1700
Data Index: 4828679 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3470. Min Range: -10.3470
Max Act: 10.2845. Min Act: -0.1700
Data Index: 3711039 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3470. Min Range: -10.3470
Max Act: 10.3470. Min Act: -0.1700
Data Index: 8318390 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3470. Min Range: -10.3470
Max Act: 10.2845. Min Act: -0.1700
Data Index: 6302708 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3470. Min Range: -10.3470
Max Act: 10.2220. Min Act: -0.1700
Data Index: 1849679 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3470. Min Range: -10.3470
Max Act: 10.0970. Min Act: -0.1700
Data Index: 6024517 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3470. Min Range: -10.3470
Max Act: 10.1595. Min Act: -0.1700
Data Index: 725305 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3470. Min Range: -10.3470
Max Act: 10.1595. Min Act: -0.1700
Data Index: 7804796 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3470. Min Range: -10.3470
Max Act: 10.2220. Min Act: -0.1700
Data Index: 5073399 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3470. Min Range: -10.3470
Max Act: 10.1595. Min Act: -0.1700
Data Index: 2135810 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3470. Min Range: -10.3470
Max Act: 10.0970. Min Act: -0.1700
Data Index: 5096663 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3470. Min Range: -10.3470
Max Act: 10.0345. Min Act: -0.1700
Data Index: 2520517 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3470. Min Range: -10.3470
Max Act: 9.9720. Min Act: -0.1700
Data Index: 6183992 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3470. Min Range: -10.3470
Max Act: 9.9720. Min Act: -0.1700
Data Index: 3935313 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3470. Min Range: -10.3470
Max Act: 9.9095. Min Act: -0.1698
Data Index: 2214465 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3470. Min Range: -10.3470
Max Act: 9.9095. Min Act: -0.1700
Data Index: 1515951 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3470. Min Range: -10.3470
Max Act: 9.8470. Min Act: -0.1700
Data Index: 5170603 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3470. Min Range: -10.3470
Max Act: 9.8470. Min Act: -0.1700
Data Index: 4440878 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3470. Min Range: -10.3470
Max Act: 9.7845. Min Act: -0.1700
Data Index: 5391789 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3470. Min Range: -10.3470
Max Act: 9.7845. Min Act: -0.1700
Data Index: 6947583 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19