Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5263 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9418. Min Range: -8.9418
Max Act: 8.9418. Min Act: -0.1700
Data Index: 5607425 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9418. Min Range: -8.9418
Max Act: 8.5043. Min Act: -0.1700
Data Index: 2971939 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9418. Min Range: -8.9418
Max Act: 8.1918. Min Act: -0.1700
Data Index: 6670980 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9418. Min Range: -8.9418
Max Act: 8.1293. Min Act: -0.1700
Data Index: 2728688 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9418. Min Range: -8.9418
Max Act: 8.1293. Min Act: -0.1700
Data Index: 4371874 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9418. Min Range: -8.9418
Max Act: 8.0668. Min Act: -0.1700
Data Index: 6996274 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9418. Min Range: -8.9418
Max Act: 8.0043. Min Act: -0.1700
Data Index: 4171726 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9418. Min Range: -8.9418
Max Act: 8.0043. Min Act: -0.1700
Data Index: 2350226 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9418. Min Range: -8.9418
Max Act: 7.8793. Min Act: -0.1700
Data Index: 5027009 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9418. Min Range: -8.9418
Max Act: 7.9418. Min Act: -0.1700
Data Index: 1150435 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9418. Min Range: -8.9418
Max Act: 7.9418. Min Act: -0.1700
Data Index: 6886556 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9418. Min Range: -8.9418
Max Act: 7.9418. Min Act: -0.1700
Data Index: 1594744 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9418. Min Range: -8.9418
Max Act: 7.9418. Min Act: -0.1700
Data Index: 8690344 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9418. Min Range: -8.9418
Max Act: 7.9418. Min Act: -0.1700
Data Index: 5337409 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9418. Min Range: -8.9418
Max Act: 7.9418. Min Act: -0.1700
Data Index: 8634329 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9418. Min Range: -8.9418
Max Act: 7.9418. Min Act: -0.1700
Data Index: 6496986 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9418. Min Range: -8.9418
Max Act: 7.9418. Min Act: -0.1700
Data Index: 6619715 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9418. Min Range: -8.9418
Max Act: 7.9418. Min Act: -0.1700
Data Index: 4975206 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9418. Min Range: -8.9418
Max Act: 7.9418. Min Act: -0.1700
Data Index: 2296450 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9418. Min Range: -8.9418
Max Act: 7.9418. Min Act: -0.1700
Data Index: 8037103 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19