Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4832 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5309. Min Range: -7.5309
Max Act: 7.5309. Min Act: -0.1700
Data Index: 7709365 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5309. Min Range: -7.5309
Max Act: 7.4684. Min Act: -0.1700
Data Index: 3736187 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5309. Min Range: -7.5309
Max Act: 7.4371. Min Act: -0.1700
Data Index: 4055459 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5309. Min Range: -7.5309
Max Act: 7.3746. Min Act: -0.1700
Data Index: 4316899 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5309. Min Range: -7.5309
Max Act: 7.3746. Min Act: -0.1700
Data Index: 5566122 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5309. Min Range: -7.5309
Max Act: 7.3434. Min Act: -0.1700
Data Index: 8478602 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.9684. Min Act: -0.1700
Data Index: 3972629 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.8746. Min Act: -0.1700
Data Index: 8518015 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.8746. Min Act: -0.1700
Data Index: 6756030 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.8434. Min Act: -0.1700
Data Index: 2964474 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.8434. Min Act: -0.1700
Data Index: 25508 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.8434. Min Act: -0.1700
Data Index: 1171976 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.8434. Min Act: -0.1700
Data Index: 6833045 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.8121. Min Act: -0.1700
Data Index: 1945524 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.8121. Min Act: -0.1700
Data Index: 6833046 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.8121. Min Act: -0.1700
Data Index: 2268149 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.7496. Min Act: -0.1700
Data Index: 6138627 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.7809. Min Act: -0.1700
Data Index: 8058774 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.7809. Min Act: -0.1700
Data Index: 6421213 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5309. Min Range: -7.5309
Max Act: 6.8121. Min Act: -0.1700
Data Index: 2673829 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19