Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4564 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.8070. Min Act: -0.1700
Data Index: 7960161 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.7445. Min Act: -0.1700
Data Index: 5310988 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.6820. Min Act: -0.1700
Data Index: 6710725 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.6820. Min Act: -0.1700
Data Index: 6224594 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.5570. Min Act: -0.1700
Data Index: 4868263 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.4945. Min Act: -0.1700
Data Index: 7960160 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.4633. Min Act: -0.1700
Data Index: 2987991 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.4633. Min Act: -0.1700
Data Index: 3837155 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.4320. Min Act: -0.1700
Data Index: 250607 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.4320. Min Act: -0.1700
Data Index: 7018477 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.4320. Min Act: -0.1700
Data Index: 4546204 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.4008. Min Act: -0.1700
Data Index: 6785765 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.4008. Min Act: -0.1700
Data Index: 730549 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.4008. Min Act: -0.1700
Data Index: 7072031 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.4008. Min Act: -0.1700
Data Index: 5757802 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.3695. Min Act: -0.1700
Data Index: 1896107 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.3383. Min Act: -0.1700
Data Index: 5986665 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.3695. Min Act: -0.1700
Data Index: 7960163 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.3695. Min Act: -0.1700
Data Index: 6791793 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8070. Min Range: -4.8070
Max Act: 4.3383. Min Act: -0.1700
Data Index: 2218572 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19