Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2808 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.1675. Min Act: -0.1700
Data Index: 3158804 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.1675. Min Act: -0.1700
Data Index: 6209036 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.1050. Min Act: -0.1700
Data Index: 3377972 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.1050. Min Act: -0.1700
Data Index: 6360735 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.0738. Min Act: -0.1700
Data Index: 2215195 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.1050. Min Act: -0.1700
Data Index: 6209047 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.0738. Min Act: -0.1700
Data Index: 2215179 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.1050. Min Act: -0.1700
Data Index: 2264936 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.0738. Min Act: -0.1700
Data Index: 3158806 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.1050. Min Act: -0.1700
Data Index: 3377963 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.0738. Min Act: -0.1700
Data Index: 6209038 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.0738. Min Act: -0.1700
Data Index: 6207935 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.1050. Min Act: -0.1700
Data Index: 3158815 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.0113. Min Act: -0.1700
Data Index: 6207945 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.0113. Min Act: -0.1700
Data Index: 4599580 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1675. Min Range: -7.1675
Max Act: 6.9800. Min Act: -0.1700
Data Index: 2134572 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1675. Min Range: -7.1675
Max Act: 6.9488. Min Act: -0.1700
Data Index: 3158817 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1675. Min Range: -7.1675
Max Act: 6.9800. Min Act: -0.1700
Data Index: 2134558 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1675. Min Range: -7.1675
Max Act: 6.9800. Min Act: -0.1700
Data Index: 2039528 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1675. Min Range: -7.1675
Max Act: 7.0113. Min Act: -0.1700
Data Index: 6360740 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19