Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3050 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.6868. Min Act: -0.1700
Data Index: 5706776 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.6555. Min Act: -0.1700
Data Index: 4994919 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.5618. Min Act: -0.1700
Data Index: 744585 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.4993. Min Act: -0.1700
Data Index: 8009582 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.4055. Min Act: -0.1700
Data Index: 4838757 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.3743. Min Act: -0.1700
Data Index: 8434457 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.3743. Min Act: -0.1700
Data Index: 240675 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.1243. Min Act: -0.1700
Data Index: 3641767 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.1243. Min Act: -0.1700
Data Index: 724873 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.1555. Min Act: -0.1700
Data Index: 7891146 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.1243. Min Act: -0.1700
Data Index: 2623458 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.0930. Min Act: -0.1700
Data Index: 2564836 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.0930. Min Act: -0.1700
Data Index: 7694769 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6868. Min Range: -7.6868
Max Act: 7.0618. Min Act: -0.1700
Data Index: 7332347 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6868. Min Range: -7.6868
Max Act: 6.9993. Min Act: -0.1700
Data Index: 5899977 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6868. Min Range: -7.6868
Max Act: 6.9993. Min Act: -0.1700
Data Index: 6161134 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6868. Min Range: -7.6868
Max Act: 6.9993. Min Act: -0.1700
Data Index: 2450386 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6868. Min Range: -7.6868
Max Act: 6.9680. Min Act: -0.1700
Data Index: 5070613 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6868. Min Range: -7.6868
Max Act: 6.9368. Min Act: -0.1700
Data Index: 866274 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6868. Min Range: -7.6868
Max Act: 6.9368. Min Act: -0.1700
Data Index: 7877803 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19