Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4502 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0689. Min Range: -6.0689
Max Act: 6.0689. Min Act: -0.1700
Data Index: 3061444 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0689. Min Range: -6.0689
Max Act: 6.0064. Min Act: -0.1700
Data Index: 2796875 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.9751. Min Act: -0.1700
Data Index: 7147655 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.9751. Min Act: -0.1700
Data Index: 885917 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.9439. Min Act: -0.1700
Data Index: 444251 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.9751. Min Act: -0.1700
Data Index: 201006 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.9126. Min Act: -0.1700
Data Index: 624862 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.9126. Min Act: -0.1700
Data Index: 7909604 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.9126. Min Act: -0.1700
Data Index: 7910677 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.9126. Min Act: -0.1700
Data Index: 3402976 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.8814. Min Act: -0.1700
Data Index: 143577 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.8814. Min Act: -0.1700
Data Index: 4110177 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.8814. Min Act: -0.1700
Data Index: 3580724 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.8814. Min Act: -0.1700
Data Index: 8184927 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.8814. Min Act: -0.1700
Data Index: 5161710 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.8814. Min Act: -0.1700
Data Index: 3358676 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.8501. Min Act: -0.1700
Data Index: 5818335 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.8501. Min Act: -0.1700
Data Index: 7192646 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.8501. Min Act: -0.1700
Data Index: 191963 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0689. Min Range: -6.0689
Max Act: 5.8501. Min Act: -0.1700
Data Index: 4134378 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19