Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4915 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.9489. Min Act: -0.1700
Data Index: 2102195 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.8864. Min Act: -0.1700
Data Index: 7032160 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.8239. Min Act: -0.1700
Data Index: 2275638 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.8239. Min Act: -0.1700
Data Index: 6290115 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.7926. Min Act: -0.1700
Data Index: 4250405 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.7614. Min Act: -0.1700
Data Index: 8733438 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.7614. Min Act: -0.1700
Data Index: 8798616 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.7614. Min Act: -0.1700
Data Index: 7774200 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.7614. Min Act: -0.1700
Data Index: 5889364 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.7614. Min Act: -0.1700
Data Index: 7426448 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.7614. Min Act: -0.1700
Data Index: 6729598 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.7301. Min Act: -0.1700
Data Index: 8180192 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.6989. Min Act: -0.1700
Data Index: 6080338 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.7301. Min Act: -0.1700
Data Index: 5517187 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.6989. Min Act: -0.1700
Data Index: 5072529 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.7301. Min Act: -0.1700
Data Index: 5220234 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.7301. Min Act: -0.1700
Data Index: 3545308 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.6989. Min Act: -0.1700
Data Index: 1619342 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.6676. Min Act: -0.1700
Data Index: 67438 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9489. Min Range: -4.9489
Max Act: 4.6676. Min Act: -0.1700
Data Index: 8668812 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19