Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1316 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.9458. Min Act: -0.1700
Data Index: 1603856 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.7895. Min Act: -0.1700
Data Index: 2500622 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.7582. Min Act: -0.1700
Data Index: 2499575 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.6018. Min Act: -0.1700
Data Index: 7932511 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.5705. Min Act: -0.1700
Data Index: 7521479 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.5861. Min Act: -0.1700
Data Index: 7221620 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.5705. Min Act: -0.1700
Data Index: 4879775 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.5548. Min Act: -0.1700
Data Index: 2443911 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.5392. Min Act: -0.1700
Data Index: 5364801 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.5548. Min Act: -0.1700
Data Index: 692161 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.5078. Min Act: -0.1700
Data Index: 7608595 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.4922. Min Act: -0.1700
Data Index: 1527604 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.4922. Min Act: -0.1700
Data Index: 2503710 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.5078. Min Act: -0.1700
Data Index: 5576976 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.5078. Min Act: -0.1700
Data Index: 6568701 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.4765. Min Act: -0.1700
Data Index: 466422 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.4608. Min Act: -0.1700
Data Index: 1808888 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.4765. Min Act: -0.1700
Data Index: 5678358 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.4765. Min Act: -0.1700
Data Index: 6111190 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9458. Min Range: -3.9458
Max Act: 3.4922. Min Act: -0.1700
Data Index: 3827465 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19