Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1756 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.8246. Min Act: -0.1700
Data Index: 8646708 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.6996. Min Act: -0.1700
Data Index: 701145 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.6996. Min Act: -0.1700
Data Index: 4357215 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.6371. Min Act: -0.1700
Data Index: 6793308 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.6058. Min Act: -0.1700
Data Index: 7843277 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.6058. Min Act: -0.1700
Data Index: 8106322 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.5746. Min Act: -0.1700
Data Index: 996813 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.5746. Min Act: -0.1700
Data Index: 163899 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.5746. Min Act: -0.1700
Data Index: 3830528 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.5746. Min Act: -0.1700
Data Index: 1511613 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.5121. Min Act: -0.1700
Data Index: 7964256 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.5433. Min Act: -0.1700
Data Index: 5997917 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.5121. Min Act: -0.1700
Data Index: 131892 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.5433. Min Act: -0.1700
Data Index: 845777 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.4808. Min Act: -0.1700
Data Index: 2006695 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.5121. Min Act: -0.1700
Data Index: 5317147 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.4496. Min Act: -0.1700
Data Index: 7670880 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.5121. Min Act: -0.1700
Data Index: 7588922 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.4808. Min Act: -0.1700
Data Index: 5699446 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8246. Min Range: -5.8246
Max Act: 5.5121. Min Act: -0.1700
Data Index: 2195043 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19