Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4111 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3947. Min Range: -6.3947
Max Act: 6.3947. Min Act: -0.1700
Data Index: 7144585 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3947. Min Range: -6.3947
Max Act: 6.2697. Min Act: -0.1700
Data Index: 1465662 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3947. Min Range: -6.3947
Max Act: 6.2072. Min Act: -0.1700
Data Index: 4369035 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3947. Min Range: -6.3947
Max Act: 6.2384. Min Act: -0.1700
Data Index: 5369893 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3947. Min Range: -6.3947
Max Act: 6.1134. Min Act: -0.1700
Data Index: 1493025 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3947. Min Range: -6.3947
Max Act: 6.0822. Min Act: -0.1700
Data Index: 7510370 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3947. Min Range: -6.3947
Max Act: 6.0509. Min Act: -0.1700
Data Index: 4716695 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3947. Min Range: -6.3947
Max Act: 6.0509. Min Act: -0.1700
Data Index: 7544160 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3947. Min Range: -6.3947
Max Act: 6.0509. Min Act: -0.1700
Data Index: 6453236 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3947. Min Range: -6.3947
Max Act: 6.0509. Min Act: -0.1700
Data Index: 7445925 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3947. Min Range: -6.3947
Max Act: 5.9572. Min Act: -0.1700
Data Index: 6854241 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3947. Min Range: -6.3947
Max Act: 5.9572. Min Act: -0.1700
Data Index: 8759369 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3947. Min Range: -6.3947
Max Act: 5.9572. Min Act: -0.1700
Data Index: 8328066 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3947. Min Range: -6.3947
Max Act: 5.9259. Min Act: -0.1700
Data Index: 8534913 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3947. Min Range: -6.3947
Max Act: 5.9259. Min Act: -0.1700
Data Index: 345483 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3947. Min Range: -6.3947
Max Act: 5.8634. Min Act: -0.1700
Data Index: 8268183 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3947. Min Range: -6.3947
Max Act: 5.8947. Min Act: -0.1700
Data Index: 6120020 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3947. Min Range: -6.3947
Max Act: 5.8634. Min Act: -0.1700
Data Index: 1365079 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3947. Min Range: -6.3947
Max Act: 5.8947. Min Act: -0.1700
Data Index: 4398808 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3947. Min Range: -6.3947
Max Act: 5.8634. Min Act: -0.1700
Data Index: 3938477 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19