Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3819 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.2944. Min Act: -0.1700
Data Index: 279434 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.2631. Min Act: -0.1700
Data Index: 4614547 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0756. Min Act: -0.1700
Data Index: 7800114 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0756. Min Act: -0.1700
Data Index: 650164 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0756. Min Act: -0.1700
Data Index: 886911 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0756. Min Act: -0.1700
Data Index: 8343847 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0756. Min Act: -0.1700
Data Index: 4415582 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0756. Min Act: -0.1700
Data Index: 1768450 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0131. Min Act: -0.1700
Data Index: 8253810 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0131. Min Act: -0.1700
Data Index: 6340075 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0444. Min Act: -0.1700
Data Index: 365080 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0444. Min Act: -0.1700
Data Index: 5722714 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0444. Min Act: -0.1700
Data Index: 4851511 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0444. Min Act: -0.1700
Data Index: 4068190 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0444. Min Act: -0.1700
Data Index: 3085864 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2944. Min Range: -4.2944
Max Act: 3.9818. Min Act: -0.1700
Data Index: 4947692 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0131. Min Act: -0.1700
Data Index: 5138938 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0131. Min Act: -0.1700
Data Index: 2922507 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0131. Min Act: -0.1700
Data Index: 718084 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2944. Min Range: -4.2944
Max Act: 4.0131. Min Act: -0.1700
Data Index: 2063311 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19