Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 790 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4538. Min Range: -7.4538
Max Act: 7.4538. Min Act: -0.1700
Data Index: 4677204 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4538. Min Range: -7.4538
Max Act: 7.1100. Min Act: -0.1700
Data Index: 3715370 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4538. Min Range: -7.4538
Max Act: 7.1413. Min Act: -0.1700
Data Index: 2710880 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.9850. Min Act: -0.1700
Data Index: 1123901 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4538. Min Range: -7.4538
Max Act: 7.0163. Min Act: -0.1700
Data Index: 850019 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.8913. Min Act: -0.1700
Data Index: 6486371 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.8288. Min Act: -0.1700
Data Index: 7593346 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.8288. Min Act: -0.1700
Data Index: 2681281 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.7975. Min Act: -0.1700
Data Index: 1023455 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.7975. Min Act: -0.1700
Data Index: 3460821 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.7350. Min Act: -0.1700
Data Index: 5554932 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.7663. Min Act: -0.1700
Data Index: 3972466 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.7663. Min Act: -0.1700
Data Index: 8802926 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.7350. Min Act: -0.1700
Data Index: 8236704 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.7350. Min Act: -0.1700
Data Index: 4305945 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.7350. Min Act: -0.1700
Data Index: 5670908 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.7350. Min Act: -0.1700
Data Index: 1859306 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.7038. Min Act: -0.1700
Data Index: 6607872 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.7350. Min Act: -0.1700
Data Index: 6492233 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4538. Min Range: -7.4538
Max Act: 6.6725. Min Act: -0.1700
Data Index: 1902530 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19