Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0695. Min Range: -8.0695
Max Act: 8.0695. Min Act: -0.1700
Data Index: 6658354 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0695. Min Range: -8.0695
Max Act: 8.0383. Min Act: -0.1700
Data Index: 8251957 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.9133. Min Act: -0.1700
Data Index: 3731852 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.8820. Min Act: -0.1700
Data Index: 3882069 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.7570. Min Act: -0.1700
Data Index: 4105819 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.7258. Min Act: -0.1700
Data Index: 3303102 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.7570. Min Act: -0.1700
Data Index: 721788 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.6633. Min Act: -0.1700
Data Index: 6684739 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.6633. Min Act: -0.1700
Data Index: 3174152 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.6008. Min Act: -0.1700
Data Index: 3731851 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.5383. Min Act: -0.1700
Data Index: 3731850 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.5383. Min Act: -0.1700
Data Index: 3823262 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.5695. Min Act: -0.1700
Data Index: 7323896 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.5383. Min Act: -0.1700
Data Index: 2978757 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.4758. Min Act: -0.1700
Data Index: 3788259 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.4758. Min Act: -0.1700
Data Index: 7212728 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.4445. Min Act: -0.1700
Data Index: 6501996 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.4445. Min Act: -0.1700
Data Index: 8656674 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.4133. Min Act: -0.1700
Data Index: 6109199 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0695. Min Range: -8.0695
Max Act: 7.4133. Min Act: -0.1700
Data Index: 6844008 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19