Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.7016. Min Act: -0.1700
Data Index: 8722236 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.7016. Min Act: -0.1700
Data Index: 7248433 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.7016. Min Act: -0.1700
Data Index: 8336952 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6929. Min Act: -0.1699
Data Index: 7593105 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6843. Min Act: -0.1700
Data Index: 5189323 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6843. Min Act: -0.1696
Data Index: 8295880 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6669. Min Act: -0.1700
Data Index: 5424640 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6756. Min Act: -0.1699
Data Index: 4068459 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6756. Min Act: -0.1700
Data Index: 5465904 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6669. Min Act: -0.1700
Data Index: 7544669 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6582. Min Act: -0.1700
Data Index: 2070299 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6582. Min Act: -0.1700
Data Index: 1263506 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6408. Min Act: -0.1699
Data Index: 3746109 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6408. Min Act: -0.1700
Data Index: 1291118 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6495. Min Act: -0.1700
Data Index: 45091 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6408. Min Act: -0.1700
Data Index: 4221983 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6408. Min Act: -0.1700
Data Index: 4848823 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6321. Min Act: -0.1700
Data Index: 8399184 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6321. Min Act: -0.1700
Data Index: 6327716 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7016. Min Range: -1.7016
Max Act: 1.6321. Min Act: -0.1699
Data Index: 5121895 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19