Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4889 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0627. Min Range: -6.0627
Max Act: 6.0627. Min Act: -0.1700
Data Index: 4522765 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0627. Min Range: -6.0627
Max Act: 6.0002. Min Act: -0.1700
Data Index: 1677500 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.9377. Min Act: -0.1700
Data Index: 5000181 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.9689. Min Act: -0.1700
Data Index: 4321448 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.7502. Min Act: -0.1700
Data Index: 196204 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.7189. Min Act: -0.1700
Data Index: 163465 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.6252. Min Act: -0.1700
Data Index: 3936615 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5314. Min Act: -0.1700
Data Index: 911194 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5314. Min Act: -0.1700
Data Index: 411219 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.5002. Min Act: -0.1700
Data Index: 8549655 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.4377. Min Act: -0.1700
Data Index: 7618731 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.4064. Min Act: -0.1700
Data Index: 4001434 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.4064. Min Act: -0.1700
Data Index: 5129298 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.3752. Min Act: -0.1700
Data Index: 7071654 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.4064. Min Act: -0.1700
Data Index: 196203 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.3439. Min Act: -0.1700
Data Index: 2566965 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.3439. Min Act: -0.1700
Data Index: 6513615 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.3127. Min Act: -0.1700
Data Index: 5564628 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.2814. Min Act: -0.1700
Data Index: 184528 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0627. Min Range: -6.0627
Max Act: 5.2814. Min Act: -0.1700
Data Index: 8084899 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19