Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5063 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0865. Min Range: -7.0865
Max Act: 7.0865. Min Act: -0.1700
Data Index: 1747000 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0865. Min Range: -7.0865
Max Act: 7.0865. Min Act: -0.1700
Data Index: 7612131 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.8052. Min Act: -0.1700
Data Index: 964144 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.7740. Min Act: -0.1700
Data Index: 5816740 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.7427. Min Act: -0.1700
Data Index: 1649041 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.7427. Min Act: -0.1700
Data Index: 360151 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.7427. Min Act: -0.1700
Data Index: 5267978 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.7427. Min Act: -0.1700
Data Index: 5175712 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.7115. Min Act: -0.1700
Data Index: 5277760 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.7115. Min Act: -0.1700
Data Index: 693437 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6802. Min Act: -0.1700
Data Index: 6494955 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6490. Min Act: -0.1700
Data Index: 4948992 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6802. Min Act: -0.1700
Data Index: 4755076 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6802. Min Act: -0.1700
Data Index: 7406019 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6490. Min Act: -0.1700
Data Index: 5948983 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6490. Min Act: -0.1700
Data Index: 5095232 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6177. Min Act: -0.1700
Data Index: 724327 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6177. Min Act: -0.1700
Data Index: 4005087 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.5865. Min Act: -0.1700
Data Index: 7369069 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0865. Min Range: -7.0865
Max Act: 6.6177. Min Act: -0.1700
Data Index: 5154956 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19