Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3142 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.8930. Min Act: -0.1700
Data Index: 3500730 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.8305. Min Act: -0.1700
Data Index: 7931998 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.7368. Min Act: -0.1700
Data Index: 8215009 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.7368. Min Act: -0.1700
Data Index: 2386566 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.6743. Min Act: -0.1700
Data Index: 5707629 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.6430. Min Act: -0.1700
Data Index: 6694804 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.6430. Min Act: -0.1700
Data Index: 5121423 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.5493. Min Act: -0.1700
Data Index: 6001670 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.5805. Min Act: -0.1700
Data Index: 549951 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.5180. Min Act: -0.1700
Data Index: 6253721 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.5180. Min Act: -0.1700
Data Index: 7490589 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.4868. Min Act: -0.1700
Data Index: 2785892 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.4868. Min Act: -0.1700
Data Index: 8520226 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.4555. Min Act: -0.1700
Data Index: 1472821 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.4555. Min Act: -0.1700
Data Index: 8405632 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.4555. Min Act: -0.1700
Data Index: 1084806 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.4243. Min Act: -0.1700
Data Index: 1500838 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.3930. Min Act: -0.1700
Data Index: 1436540 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.3618. Min Act: -0.1700
Data Index: 2324751 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8930. Min Range: -5.8930
Max Act: 5.3618. Min Act: -0.1700
Data Index: 5146536 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19