Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4534 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2000. Min Range: -6.2000
Max Act: 6.2000. Min Act: -0.1700
Data Index: 7302598 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2000. Min Range: -6.2000
Max Act: 6.0437. Min Act: -0.1700
Data Index: 400400 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2000. Min Range: -6.2000
Max Act: 6.0437. Min Act: -0.1700
Data Index: 5778185 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2000. Min Range: -6.2000
Max Act: 6.0437. Min Act: -0.1700
Data Index: 7787427 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2000. Min Range: -6.2000
Max Act: 6.0125. Min Act: -0.1700
Data Index: 6874226 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9812. Min Act: -0.1700
Data Index: 2445756 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9812. Min Act: -0.1700
Data Index: 6975504 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9500. Min Act: -0.1700
Data Index: 6603621 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9500. Min Act: -0.1700
Data Index: 7998381 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9500. Min Act: -0.1700
Data Index: 7787421 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9187. Min Act: -0.1700
Data Index: 7787424 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9187. Min Act: -0.1700
Data Index: 2366802 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9187. Min Act: -0.1700
Data Index: 7787431 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9187. Min Act: -0.1700
Data Index: 364370 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9187. Min Act: -0.1700
Data Index: 351961 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9187. Min Act: -0.1700
Data Index: 2974171 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.8875. Min Act: -0.1700
Data Index: 6580416 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.8875. Min Act: -0.1700
Data Index: 3998518 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9187. Min Act: -0.1700
Data Index: 5862816 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2000. Min Range: -6.2000
Max Act: 5.9187. Min Act: -0.1700
Data Index: 4569501 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19