Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0974. Min Range: -5.0974
Max Act: 5.0974. Min Act: -0.1700
Data Index: 5180378 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0974. Min Range: -5.0974
Max Act: 5.0037. Min Act: -0.1700
Data Index: 4678101 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.9412. Min Act: -0.1700
Data Index: 5900086 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.8787. Min Act: -0.1700
Data Index: 2212488 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.8787. Min Act: -0.1700
Data Index: 3609736 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.8474. Min Act: -0.1700
Data Index: 4483664 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.8787. Min Act: -0.1700
Data Index: 2892554 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.8162. Min Act: -0.1700
Data Index: 3616168 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.7849. Min Act: -0.1700
Data Index: 6751688 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.7849. Min Act: -0.1700
Data Index: 6752294 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.7849. Min Act: -0.1700
Data Index: 1535828 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.7537. Min Act: -0.1700
Data Index: 1050507 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.7224. Min Act: -0.1700
Data Index: 4401356 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.6912. Min Act: -0.1700
Data Index: 6988683 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.7224. Min Act: -0.1700
Data Index: 1526583 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.7537. Min Act: -0.1700
Data Index: 4976755 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.6912. Min Act: -0.1700
Data Index: 6563163 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.6912. Min Act: -0.1700
Data Index: 307381 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.6912. Min Act: -0.1700
Data Index: 5845614 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0974. Min Range: -5.0974
Max Act: 4.6599. Min Act: -0.1700
Data Index: 4944101 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19