Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1298 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.9710. Min Act: -0.1700
Data Index: 3092889 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8929. Min Act: -0.1700
Data Index: 4363619 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8929. Min Act: -0.1700
Data Index: 752882 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8460. Min Act: -0.1700
Data Index: 5193783 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8460. Min Act: -0.1700
Data Index: 3152858 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8460. Min Act: -0.1700
Data Index: 7499861 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8303. Min Act: -0.1700
Data Index: 2893884 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8460. Min Act: -0.1700
Data Index: 8250118 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8303. Min Act: -0.1700
Data Index: 106259 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8147. Min Act: -0.1700
Data Index: 5421035 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8147. Min Act: -0.1700
Data Index: 4210364 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8303. Min Act: -0.1700
Data Index: 2677386 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.7991. Min Act: -0.1700
Data Index: 5186749 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8147. Min Act: -0.1700
Data Index: 4658055 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.8147. Min Act: -0.1700
Data Index: 862413 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.7834. Min Act: -0.1700
Data Index: 1371059 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.7834. Min Act: -0.1700
Data Index: 7126665 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.7678. Min Act: -0.1700
Data Index: 7466094 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.7678. Min Act: -0.1700
Data Index: 8567376 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9710. Min Range: -3.9710
Max Act: 3.7834. Min Act: -0.1700
Data Index: 3181439 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19