Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3880 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.8488. Min Act: -0.1700
Data Index: 6672643 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.5988. Min Act: -0.1700
Data Index: 8297026 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.5675. Min Act: -0.1700
Data Index: 2909428 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.5675. Min Act: -0.1700
Data Index: 2121386 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.5675. Min Act: -0.1700
Data Index: 4490772 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.5363. Min Act: -0.1700
Data Index: 8756776 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.5363. Min Act: -0.1700
Data Index: 40442 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.5050. Min Act: -0.1700
Data Index: 8206600 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.4738. Min Act: -0.1700
Data Index: 7726939 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.4425. Min Act: -0.1700
Data Index: 5143175 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.4425. Min Act: -0.1700
Data Index: 2366052 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.4425. Min Act: -0.1700
Data Index: 494545 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.4425. Min Act: -0.1700
Data Index: 5536890 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.4113. Min Act: -0.1700
Data Index: 3332459 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.3800. Min Act: -0.1700
Data Index: 656741 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.3488. Min Act: -0.1700
Data Index: 3173852 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.3488. Min Act: -0.1700
Data Index: 8447961 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.3488. Min Act: -0.1700
Data Index: 8326643 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.3488. Min Act: -0.1700
Data Index: 5665358 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8488. Min Range: -7.8488
Max Act: 7.3488. Min Act: -0.1700
Data Index: 5432673 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19