Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 428 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2171. Min Range: -6.2171
Max Act: 6.2171. Min Act: -0.1700
Data Index: 7673148 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.7171. Min Act: -0.1700
Data Index: 5697215 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.7171. Min Act: -0.1700
Data Index: 6174431 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.7171. Min Act: -0.1700
Data Index: 6615931 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.7171. Min Act: -0.1700
Data Index: 3239196 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.6859. Min Act: -0.1700
Data Index: 731559 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.6859. Min Act: -0.1700
Data Index: 5017811 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.6859. Min Act: -0.1700
Data Index: 8363182 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.6234. Min Act: -0.1700
Data Index: 4013932 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.6546. Min Act: -0.1700
Data Index: 7485148 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.6859. Min Act: -0.1700
Data Index: 8750494 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.6234. Min Act: -0.1700
Data Index: 5744577 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.5921. Min Act: -0.1700
Data Index: 4164689 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.6234. Min Act: -0.1700
Data Index: 2157332 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.5921. Min Act: -0.1700
Data Index: 1415018 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.6234. Min Act: -0.1700
Data Index: 2724359 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.6234. Min Act: -0.1700
Data Index: 2598058 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.5921. Min Act: -0.1700
Data Index: 8697561 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.5921. Min Act: -0.1700
Data Index: 8341419 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2171. Min Range: -6.2171
Max Act: 5.6234. Min Act: -0.1700
Data Index: 4857666 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19