Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 367 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2987. Min Range: -6.2987
Max Act: 6.2987. Min Act: -0.1700
Data Index: 1316276 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2987. Min Range: -6.2987
Max Act: 6.2362. Min Act: -0.1700
Data Index: 6942070 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2987. Min Range: -6.2987
Max Act: 6.1737. Min Act: -0.1700
Data Index: 7793339 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2987. Min Range: -6.2987
Max Act: 6.2050. Min Act: -0.1700
Data Index: 1319573 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.9862. Min Act: -0.1700
Data Index: 6746506 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2987. Min Range: -6.2987
Max Act: 6.0487. Min Act: -0.1700
Data Index: 5670388 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.9862. Min Act: -0.1700
Data Index: 1897322 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.9862. Min Act: -0.1700
Data Index: 3678997 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.9550. Min Act: -0.1700
Data Index: 6982800 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.9237. Min Act: -0.1700
Data Index: 4157105 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.9237. Min Act: -0.1700
Data Index: 2341938 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.9550. Min Act: -0.1700
Data Index: 6433059 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.8925. Min Act: -0.1700
Data Index: 2073263 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.8925. Min Act: -0.1700
Data Index: 3488625 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.8925. Min Act: -0.1700
Data Index: 3827883 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.8612. Min Act: -0.1700
Data Index: 3024345 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.8300. Min Act: -0.1700
Data Index: 6536762 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.8300. Min Act: -0.1700
Data Index: 4821436 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.7675. Min Act: -0.1700
Data Index: 622677 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2987. Min Range: -6.2987
Max Act: 5.8300. Min Act: -0.1700
Data Index: 5982869 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19