Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2198 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.9977. Min Act: -0.1700
Data Index: 5271406 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.9352. Min Act: -0.1700
Data Index: 1194781 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.7477. Min Act: -0.1700
Data Index: 3975353 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.6852. Min Act: -0.1700
Data Index: 8528977 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.6540. Min Act: -0.1700
Data Index: 387559 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.6540. Min Act: -0.1700
Data Index: 344888 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.6227. Min Act: -0.1700
Data Index: 3566356 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.6227. Min Act: -0.1700
Data Index: 4725332 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.5915. Min Act: -0.1700
Data Index: 8555798 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.5290. Min Act: -0.1700
Data Index: 6339301 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.5290. Min Act: -0.1700
Data Index: 6140178 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.5290. Min Act: -0.1700
Data Index: 2542233 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.5290. Min Act: -0.1700
Data Index: 3167780 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.5290. Min Act: -0.1700
Data Index: 3333654 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.4977. Min Act: -0.1700
Data Index: 979600 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.4665. Min Act: -0.1700
Data Index: 3658446 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.4665. Min Act: -0.1700
Data Index: 1810021 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.4352. Min Act: -0.1700
Data Index: 4022100 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.4352. Min Act: -0.1700
Data Index: 3581676 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9977. Min Range: -5.9977
Max Act: 5.4352. Min Act: -0.1700
Data Index: 2520744 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19