Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2934 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4141. Min Range: -9.4141
Max Act: 9.4141. Min Act: -0.1700
Data Index: 6327620 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4141. Min Range: -9.4141
Max Act: 9.4141. Min Act: -0.1700
Data Index: 2855620 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4141. Min Range: -9.4141
Max Act: 9.2266. Min Act: -0.1700
Data Index: 11811 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4141. Min Range: -9.4141
Max Act: 9.0391. Min Act: -0.1700
Data Index: 11812 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.9141. Min Act: -0.1700
Data Index: 7635860 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.9141. Min Act: -0.1700
Data Index: 327522 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.9141. Min Act: -0.1700
Data Index: 963011 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.8516. Min Act: -0.1700
Data Index: 7635859 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.8516. Min Act: -0.1700
Data Index: 2954409 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.7266. Min Act: -0.1700
Data Index: 8315412 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.6641. Min Act: -0.1700
Data Index: 2855618 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.7266. Min Act: -0.1700
Data Index: 963023 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.6641. Min Act: -0.1700
Data Index: 1050044 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.6016. Min Act: -0.1700
Data Index: 5430339 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.6016. Min Act: -0.1700
Data Index: 3229930 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.5391. Min Act: -0.1700
Data Index: 4960308 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.4766. Min Act: -0.1700
Data Index: 521800 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.5391. Min Act: -0.1700
Data Index: 3684631 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.4766. Min Act: -0.1700
Data Index: 963014 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4141. Min Range: -9.4141
Max Act: 8.5391. Min Act: -0.1700
Data Index: 3877980 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19