Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.4122. Min Act: -0.1700
Data Index: 4758579 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.4122. Min Act: -0.1700
Data Index: 8433064 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.3497. Min Act: -0.1700
Data Index: 1903462 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.3184. Min Act: -0.1700
Data Index: 8511535 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.1934. Min Act: -0.1700
Data Index: 5397283 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.1622. Min Act: -0.1700
Data Index: 5608378 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.1622. Min Act: -0.1700
Data Index: 5837972 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.0997. Min Act: -0.1700
Data Index: 898735 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.0997. Min Act: -0.1700
Data Index: 717578 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.0684. Min Act: -0.1700
Data Index: 4283269 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.0372. Min Act: -0.1700
Data Index: 7554253 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.0684. Min Act: -0.1700
Data Index: 1170496 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.0684. Min Act: -0.1700
Data Index: 6910228 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.0372. Min Act: -0.1700
Data Index: 1865633 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.0059. Min Act: -0.1700
Data Index: 6886049 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.0059. Min Act: -0.1700
Data Index: 7996377 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4122. Min Range: -5.4122
Max Act: 5.0059. Min Act: -0.1700
Data Index: 6610434 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4122. Min Range: -5.4122
Max Act: 4.9747. Min Act: -0.1700
Data Index: 5815210 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4122. Min Range: -5.4122
Max Act: 4.9747. Min Act: -0.1700
Data Index: 5353160 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4122. Min Range: -5.4122
Max Act: 4.9747. Min Act: -0.1700
Data Index: 7098547 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19