Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0732. Min Range: -9.0732
Max Act: 9.0732. Min Act: -0.1700
Data Index: 690496 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0732. Min Range: -9.0732
Max Act: 9.0732. Min Act: -0.1700
Data Index: 5241946 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.9482. Min Act: -0.1700
Data Index: 3798239 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.9482. Min Act: -0.1700
Data Index: 79576 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.8232. Min Act: -0.1700
Data Index: 6776722 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.7607. Min Act: -0.1700
Data Index: 3443321 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.7607. Min Act: -0.1700
Data Index: 6616936 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.6982. Min Act: -0.1700
Data Index: 8314545 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.6982. Min Act: -0.1700
Data Index: 1265641 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.6982. Min Act: -0.1700
Data Index: 4784753 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.6982. Min Act: -0.1700
Data Index: 1727104 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.6357. Min Act: -0.1700
Data Index: 5441600 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.5732. Min Act: -0.1700
Data Index: 3401205 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.5732. Min Act: -0.1700
Data Index: 4359641 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.5107. Min Act: -0.1700
Data Index: 235277 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.5732. Min Act: -0.1700
Data Index: 3646234 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.5107. Min Act: -0.1700
Data Index: 4643875 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.5107. Min Act: -0.1700
Data Index: 1501171 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.4482. Min Act: -0.1700
Data Index: 2685505 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0732. Min Range: -9.0732
Max Act: 8.5107. Min Act: -0.1700
Data Index: 458571 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19