Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 835 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.1923. Min Act: -0.1700
Data Index: 4564472 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.1298. Min Act: -0.1700
Data Index: 6373748 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.1298. Min Act: -0.1700
Data Index: 8505519 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.0985. Min Act: -0.1700
Data Index: 1837571 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.0673. Min Act: -0.1700
Data Index: 3135295 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.0360. Min Act: -0.1700
Data Index: 5344473 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.0360. Min Act: -0.1700
Data Index: 3801617 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.0360. Min Act: -0.1700
Data Index: 3868599 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.0360. Min Act: -0.1700
Data Index: 7553167 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.0360. Min Act: -0.1700
Data Index: 3949955 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.0048. Min Act: -0.1700
Data Index: 5175422 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.0048. Min Act: -0.1700
Data Index: 4656211 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.0048. Min Act: -0.1700
Data Index: 1367493 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1923. Min Range: -5.1923
Max Act: 5.0360. Min Act: -0.1700
Data Index: 570463 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1923. Min Range: -5.1923
Max Act: 4.9735. Min Act: -0.1700
Data Index: 5175425 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1923. Min Range: -5.1923
Max Act: 4.9735. Min Act: -0.1700
Data Index: 8716695 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1923. Min Range: -5.1923
Max Act: 4.9735. Min Act: -0.1700
Data Index: 5935318 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1923. Min Range: -5.1923
Max Act: 4.9735. Min Act: -0.1700
Data Index: 1903745 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1923. Min Range: -5.1923
Max Act: 4.9423. Min Act: -0.1700
Data Index: 477684 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1923. Min Range: -5.1923
Max Act: 4.9423. Min Act: -0.1700
Data Index: 3949960 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19