Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6049 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.4125. Min Act: -0.1700
Data Index: 5752606 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.2875. Min Act: -0.1700
Data Index: 1531273 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.1312. Min Act: -0.1700
Data Index: 7325806 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.1312. Min Act: -0.1700
Data Index: 7240222 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.1000. Min Act: -0.1700
Data Index: 1407077 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.0687. Min Act: -0.1700
Data Index: 8386512 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.0687. Min Act: -0.1700
Data Index: 1624278 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.0375. Min Act: -0.1700
Data Index: 7462775 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.0062. Min Act: -0.1700
Data Index: 3105397 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.0375. Min Act: -0.1700
Data Index: 2881036 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.0375. Min Act: -0.1700
Data Index: 6103453 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.0062. Min Act: -0.1700
Data Index: 3060443 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.0062. Min Act: -0.1700
Data Index: 988930 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.0062. Min Act: -0.1700
Data Index: 1656591 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4125. Min Range: -6.4125
Max Act: 5.9750. Min Act: -0.1700
Data Index: 4659515 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4125. Min Range: -6.4125
Max Act: 5.9750. Min Act: -0.1700
Data Index: 6635647 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4125. Min Range: -6.4125
Max Act: 6.0062. Min Act: -0.1700
Data Index: 7969739 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4125. Min Range: -6.4125
Max Act: 5.9750. Min Act: -0.1700
Data Index: 1416565 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4125. Min Range: -6.4125
Max Act: 5.9750. Min Act: -0.1700
Data Index: 1657537 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4125. Min Range: -6.4125
Max Act: 5.9750. Min Act: -0.1700
Data Index: 5710649 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19