Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3868 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1045. Min Range: -5.1045
Max Act: 5.1045. Min Act: -0.1700
Data Index: 5546496 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.9795. Min Act: -0.1700
Data Index: 8111468 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1045. Min Range: -5.1045
Max Act: 5.0107. Min Act: -0.1700
Data Index: 3563792 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.9482. Min Act: -0.1700
Data Index: 4116387 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.8545. Min Act: -0.1700
Data Index: 8832030 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.8545. Min Act: -0.1700
Data Index: 8041174 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.8232. Min Act: -0.1700
Data Index: 8830488 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.7920. Min Act: -0.1700
Data Index: 8496057 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.7607. Min Act: -0.1700
Data Index: 5309614 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.7295. Min Act: -0.1700
Data Index: 3498496 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.7607. Min Act: -0.1700
Data Index: 4544281 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.7295. Min Act: -0.1700
Data Index: 2413055 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.7295. Min Act: -0.1700
Data Index: 8787849 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.6982. Min Act: -0.1700
Data Index: 7414296 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.6982. Min Act: -0.1700
Data Index: 3308148 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.6982. Min Act: -0.1700
Data Index: 3257692 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.6982. Min Act: -0.1700
Data Index: 4240421 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.6982. Min Act: -0.1700
Data Index: 1094831 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.6982. Min Act: -0.1700
Data Index: 5559251 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1045. Min Range: -5.1045
Max Act: 4.6670. Min Act: -0.1700
Data Index: 629539 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19