Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8962. Min Act: -0.1700
Data Index: 6976952 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8877. Min Act: -0.1700
Data Index: 3339186 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8877. Min Act: -0.1695
Data Index: 7123609 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8877. Min Act: -0.1700
Data Index: 1091778 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8536. Min Act: -0.1689
Data Index: 3951500 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8452. Min Act: -0.1699
Data Index: 4704214 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8452. Min Act: -0.1700
Data Index: 925293 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8452. Min Act: -0.1700
Data Index: 3635716 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8536. Min Act: -0.1700
Data Index: 2953132 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8282. Min Act: -0.1699
Data Index: 1355035 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8367. Min Act: -0.1700
Data Index: 4475754 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8282. Min Act: -0.1700
Data Index: 4775712 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8198. Min Act: -0.1699
Data Index: 1409452 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8198. Min Act: -0.1700
Data Index: 4786405 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8198. Min Act: -0.1700
Data Index: 1827316 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8114. Min Act: -0.1698
Data Index: 6651999 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8114. Min Act: -0.1699
Data Index: 6976951 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8030. Min Act: -0.1699
Data Index: 2037268 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.7946. Min Act: -0.1700
Data Index: 6094450 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8962. Min Range: -0.8962
Max Act: 0.8114. Min Act: -0.1700
Data Index: 1597589 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19