Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6065 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.4010. Min Act: -0.1700
Data Index: 7489847 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.3698. Min Act: -0.1700
Data Index: 3568470 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.2448. Min Act: -0.1700
Data Index: 6519524 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.2448. Min Act: -0.1700
Data Index: 8828623 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.1823. Min Act: -0.1700
Data Index: 4893595 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.1823. Min Act: -0.1700
Data Index: 6857535 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.1510. Min Act: -0.1700
Data Index: 8389050 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.0885. Min Act: -0.1700
Data Index: 5848080 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.0885. Min Act: -0.1700
Data Index: 7666654 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.1198. Min Act: -0.1700
Data Index: 7762270 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.0885. Min Act: -0.1700
Data Index: 916138 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.0885. Min Act: -0.1700
Data Index: 3755888 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.0885. Min Act: -0.1700
Data Index: 3431672 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.0573. Min Act: -0.1700
Data Index: 4168493 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.0260. Min Act: -0.1700
Data Index: 4793156 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.0573. Min Act: -0.1700
Data Index: 6273949 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.0573. Min Act: -0.1700
Data Index: 4073049 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.0260. Min Act: -0.1700
Data Index: 6372249 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.0260. Min Act: -0.1700
Data Index: 914070 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4010. Min Range: -6.4010
Max Act: 6.0260. Min Act: -0.1700
Data Index: 1548630 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19