Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2120 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.9006. Min Act: -0.1700
Data Index: 7910302 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.8381. Min Act: -0.1700
Data Index: 7180569 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.8068. Min Act: -0.1700
Data Index: 2989977 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.8068. Min Act: -0.1700
Data Index: 5202148 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.7756. Min Act: -0.1700
Data Index: 6933980 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.7131. Min Act: -0.1700
Data Index: 1168290 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.7131. Min Act: -0.1700
Data Index: 4835148 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.7131. Min Act: -0.1700
Data Index: 7305098 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.6818. Min Act: -0.1700
Data Index: 6293783 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.6506. Min Act: -0.1700
Data Index: 7771333 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.6506. Min Act: -0.1700
Data Index: 8060692 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.6193. Min Act: -0.1700
Data Index: 2925812 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.6193. Min Act: -0.1700
Data Index: 1280144 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.6193. Min Act: -0.1700
Data Index: 3920103 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.6193. Min Act: -0.1700
Data Index: 4553838 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.6193. Min Act: -0.1700
Data Index: 6853014 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.5568. Min Act: -0.1700
Data Index: 7746138 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.5568. Min Act: -0.1700
Data Index: 378064 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.5568. Min Act: -0.1700
Data Index: 5048133 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9006. Min Range: -5.9006
Max Act: 5.5568. Min Act: -0.1700
Data Index: 506600 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19