Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2682 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0743. Min Range: -5.0743
Max Act: 5.0743. Min Act: -0.1700
Data Index: 6602109 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.8555. Min Act: -0.1700
Data Index: 4297481 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.8243. Min Act: -0.1700
Data Index: 7591550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.8555. Min Act: -0.1700
Data Index: 3192130 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.7930. Min Act: -0.1700
Data Index: 8415544 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.7618. Min Act: -0.1700
Data Index: 2541513 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.7618. Min Act: -0.1700
Data Index: 6568531 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.6368. Min Act: -0.1700
Data Index: 4667927 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.6993. Min Act: -0.1700
Data Index: 5095805 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.6055. Min Act: -0.1700
Data Index: 3128098 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.6055. Min Act: -0.1700
Data Index: 3942719 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.6055. Min Act: -0.1700
Data Index: 6100769 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.5430. Min Act: -0.1700
Data Index: 2788214 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.5430. Min Act: -0.1700
Data Index: 566011 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.4805. Min Act: -0.1700
Data Index: 7917074 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.5118. Min Act: -0.1700
Data Index: 2260153 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.4493. Min Act: -0.1700
Data Index: 8573809 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.4493. Min Act: -0.1700
Data Index: 2318563 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.4180. Min Act: -0.1700
Data Index: 886520 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0743. Min Range: -5.0743
Max Act: 4.4180. Min Act: -0.1700
Data Index: 5316185 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19