Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4870 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.3948. Min Act: -0.1700
Data Index: 3179848 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.3011. Min Act: -0.1700
Data Index: 7269492 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.3011. Min Act: -0.1700
Data Index: 62875 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.2073. Min Act: -0.1700
Data Index: 4316681 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1761. Min Act: -0.1700
Data Index: 373949 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1448. Min Act: -0.1700
Data Index: 1142671 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1448. Min Act: -0.1700
Data Index: 5377205 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1136. Min Act: -0.1700
Data Index: 7978656 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.1136. Min Act: -0.1700
Data Index: 8566209 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0823. Min Act: -0.1700
Data Index: 2725898 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0823. Min Act: -0.1700
Data Index: 6823065 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0511. Min Act: -0.1700
Data Index: 5221368 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0511. Min Act: -0.1700
Data Index: 2469730 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0511. Min Act: -0.1700
Data Index: 1142668 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0198. Min Act: -0.1700
Data Index: 1541543 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0198. Min Act: -0.1700
Data Index: 4948453 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3948. Min Range: -5.3948
Max Act: 5.0198. Min Act: -0.1700
Data Index: 7284900 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.9886. Min Act: -0.1700
Data Index: 1318783 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.9886. Min Act: -0.1700
Data Index: 1142664 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3948. Min Range: -5.3948
Max Act: 4.9886. Min Act: -0.1700
Data Index: 4257656 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19