Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5430 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1591. Min Range: -6.1591
Max Act: 6.1591. Min Act: -0.1700
Data Index: 3443154 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1591. Min Range: -6.1591
Max Act: 6.1591. Min Act: -0.1700
Data Index: 3796792 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1591. Min Range: -6.1591
Max Act: 6.1278. Min Act: -0.1700
Data Index: 4918188 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1591. Min Range: -6.1591
Max Act: 6.0653. Min Act: -0.1700
Data Index: 7096485 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1591. Min Range: -6.1591
Max Act: 6.0653. Min Act: -0.1700
Data Index: 7109477 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1591. Min Range: -6.1591
Max Act: 6.0341. Min Act: -0.1700
Data Index: 8024548 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1591. Min Range: -6.1591
Max Act: 6.0028. Min Act: -0.1700
Data Index: 4412955 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1591. Min Range: -6.1591
Max Act: 6.0028. Min Act: -0.1700
Data Index: 5735489 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.9403. Min Act: -0.1700
Data Index: 2741252 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.9716. Min Act: -0.1700
Data Index: 5082960 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.9716. Min Act: -0.1700
Data Index: 2963799 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.9716. Min Act: -0.1700
Data Index: 4779921 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.9091. Min Act: -0.1700
Data Index: 625234 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.9091. Min Act: -0.1700
Data Index: 5795080 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.8778. Min Act: -0.1700
Data Index: 5024175 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.8778. Min Act: -0.1700
Data Index: 939332 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.8466. Min Act: -0.1700
Data Index: 2173621 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.8466. Min Act: -0.1700
Data Index: 7850723 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.8153. Min Act: -0.1700
Data Index: 99514 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1591. Min Range: -6.1591
Max Act: 5.8153. Min Act: -0.1700
Data Index: 2100951 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19