Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5118 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0260. Min Range: -6.0260
Max Act: 6.0260. Min Act: -0.1700
Data Index: 7960161 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.9635. Min Act: -0.1700
Data Index: 7661159 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.9010. Min Act: -0.1700
Data Index: 2236933 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.9010. Min Act: -0.1700
Data Index: 464005 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.8385. Min Act: -0.1700
Data Index: 4595627 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.8073. Min Act: -0.1700
Data Index: 8697108 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.7760. Min Act: -0.1700
Data Index: 8733319 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.8385. Min Act: -0.1700
Data Index: 8165948 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.8073. Min Act: -0.1700
Data Index: 3773940 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.7760. Min Act: -0.1700
Data Index: 5316571 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.8073. Min Act: -0.1700
Data Index: 6817575 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.7760. Min Act: -0.1700
Data Index: 6066039 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.7448. Min Act: -0.1700
Data Index: 5376167 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.7135. Min Act: -0.1700
Data Index: 7962491 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.7135. Min Act: -0.1700
Data Index: 8297969 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.6823. Min Act: -0.1700
Data Index: 1541800 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.6823. Min Act: -0.1700
Data Index: 5661185 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.7135. Min Act: -0.1700
Data Index: 3450895 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.7135. Min Act: -0.1700
Data Index: 3597191 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.6823. Min Act: -0.1700
Data Index: 5072096 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19