Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2809 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.2397. Min Act: -0.1700
Data Index: 5592520 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.2397. Min Act: -0.1700
Data Index: 5949650 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.2085. Min Act: -0.1700
Data Index: 665365 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.1772. Min Act: -0.1700
Data Index: 1292778 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.1460. Min Act: -0.1700
Data Index: 5633936 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.1147. Min Act: -0.1700
Data Index: 2271971 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.1147. Min Act: -0.1700
Data Index: 7153766 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.0835. Min Act: -0.1700
Data Index: 5798460 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.0835. Min Act: -0.1700
Data Index: 7972973 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.0835. Min Act: -0.1700
Data Index: 3997525 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.0522. Min Act: -0.1700
Data Index: 2428831 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.0522. Min Act: -0.1700
Data Index: 6263628 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.0522. Min Act: -0.1700
Data Index: 8752160 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.0522. Min Act: -0.1700
Data Index: 5928584 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.0522. Min Act: -0.1700
Data Index: 635827 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.0210. Min Act: -0.1700
Data Index: 5980225 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2397. Min Range: -5.2397
Max Act: 4.9897. Min Act: -0.1700
Data Index: 1224323 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.0210. Min Act: -0.1700
Data Index: 52052 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2397. Min Range: -5.2397
Max Act: 4.9897. Min Act: -0.1700
Data Index: 8543116 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2397. Min Range: -5.2397
Max Act: 5.0210. Min Act: -0.1700
Data Index: 2380096 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19