Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3596 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0229. Min Range: -5.0229
Max Act: 5.0229. Min Act: -0.1700
Data Index: 4417803 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.9916. Min Act: -0.1700
Data Index: 7978310 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.9604. Min Act: -0.1700
Data Index: 2467906 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.8666. Min Act: -0.1700
Data Index: 6518087 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.8041. Min Act: -0.1700
Data Index: 4917817 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.8041. Min Act: -0.1700
Data Index: 3832110 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.7416. Min Act: -0.1700
Data Index: 3161035 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.7416. Min Act: -0.1700
Data Index: 3653522 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.7104. Min Act: -0.1700
Data Index: 1393207 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.6479. Min Act: -0.1700
Data Index: 2742668 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.6479. Min Act: -0.1700
Data Index: 1275709 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.6166. Min Act: -0.1700
Data Index: 3451466 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.6166. Min Act: -0.1700
Data Index: 4133277 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.5854. Min Act: -0.1700
Data Index: 988211 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.5541. Min Act: -0.1700
Data Index: 433173 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.5854. Min Act: -0.1700
Data Index: 2399378 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.5854. Min Act: -0.1700
Data Index: 2263160 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.5854. Min Act: -0.1700
Data Index: 1046673 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.5541. Min Act: -0.1700
Data Index: 3271240 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0229. Min Range: -5.0229
Max Act: 4.5541. Min Act: -0.1700
Data Index: 6482711 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19