Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.8310. Min Act: -0.1700
Data Index: 8235024 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.7372. Min Act: -0.1700
Data Index: 2476288 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.7685. Min Act: -0.1700
Data Index: 7972694 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.7060. Min Act: -0.1700
Data Index: 1896554 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.7060. Min Act: -0.1700
Data Index: 3439867 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.7060. Min Act: -0.1700
Data Index: 431922 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.6435. Min Act: -0.1700
Data Index: 1862868 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.6435. Min Act: -0.1700
Data Index: 2548424 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.6122. Min Act: -0.1700
Data Index: 2548426 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.6435. Min Act: -0.1700
Data Index: 3747445 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.6122. Min Act: -0.1700
Data Index: 7409755 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.5810. Min Act: -0.1700
Data Index: 3194402 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.5497. Min Act: -0.1700
Data Index: 6420846 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.5497. Min Act: -0.1700
Data Index: 1896553 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.5810. Min Act: -0.1700
Data Index: 2776554 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.5497. Min Act: -0.1700
Data Index: 3587917 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.5497. Min Act: -0.1700
Data Index: 6614327 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.5497. Min Act: -0.1700
Data Index: 5829699 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.5185. Min Act: -0.1700
Data Index: 3439861 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8310. Min Range: -5.8310
Max Act: 5.5185. Min Act: -0.1700
Data Index: 727979 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19