Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.7607. Min Act: -0.1700
Data Index: 6510057 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.6670. Min Act: -0.1700
Data Index: 7134593 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.6670. Min Act: -0.1700
Data Index: 3248411 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.6670. Min Act: -0.1700
Data Index: 5755079 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.6045. Min Act: -0.1700
Data Index: 3248410 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.5732. Min Act: -0.1700
Data Index: 5645481 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.5732. Min Act: -0.1700
Data Index: 6761464 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.5420. Min Act: -0.1700
Data Index: 7067936 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.5420. Min Act: -0.1700
Data Index: 5157309 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.4795. Min Act: -0.1700
Data Index: 3443121 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.5107. Min Act: -0.1700
Data Index: 7989876 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.5107. Min Act: -0.1700
Data Index: 618008 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.4795. Min Act: -0.1700
Data Index: 3930951 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.4482. Min Act: -0.1700
Data Index: 2924684 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.4482. Min Act: -0.1700
Data Index: 1391021 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.4482. Min Act: -0.1700
Data Index: 7711752 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.4482. Min Act: -0.1700
Data Index: 2392068 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.4170. Min Act: -0.1700
Data Index: 5867481 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.4170. Min Act: -0.1700
Data Index: 6293125 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7607. Min Range: -6.7607
Max Act: 6.4482. Min Act: -0.1700
Data Index: 2459273 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19