Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5865 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1556. Min Range: -9.1556
Max Act: 9.1556. Min Act: -0.1700
Data Index: 5802439 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.9056. Min Act: -0.1700
Data Index: 5233386 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.7181. Min Act: -0.1700
Data Index: 4484108 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.6556. Min Act: -0.1700
Data Index: 3494312 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.5306. Min Act: -0.1700
Data Index: 7552067 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.5306. Min Act: -0.1700
Data Index: 5583059 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.5931. Min Act: -0.1700
Data Index: 1641921 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.5306. Min Act: -0.1700
Data Index: 5450465 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.4681. Min Act: -0.1700
Data Index: 5536828 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.4681. Min Act: -0.1700
Data Index: 1804963 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.4056. Min Act: -0.1700
Data Index: 3189470 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.4056. Min Act: -0.1700
Data Index: 2181899 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.3431. Min Act: -0.1700
Data Index: 2185801 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.2806. Min Act: -0.1700
Data Index: 4813582 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.3431. Min Act: -0.1700
Data Index: 1519096 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.3431. Min Act: -0.1700
Data Index: 4650445 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.3431. Min Act: -0.1700
Data Index: 954335 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.3431. Min Act: -0.1700
Data Index: 4289584 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.3431. Min Act: -0.1700
Data Index: 6230966 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1556. Min Range: -9.1556
Max Act: 8.4056. Min Act: -0.1700
Data Index: 2753398 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19