Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2040 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.8110. Min Act: -0.1700
Data Index: 3828210 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.8110. Min Act: -0.1700
Data Index: 6441012 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.7172. Min Act: -0.1700
Data Index: 5037488 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.7172. Min Act: -0.1700
Data Index: 88276 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.6547. Min Act: -0.1700
Data Index: 8461862 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.6235. Min Act: -0.1700
Data Index: 6705802 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.6235. Min Act: -0.1700
Data Index: 316867 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.6235. Min Act: -0.1700
Data Index: 1450438 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.6235. Min Act: -0.1700
Data Index: 8071090 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.5610. Min Act: -0.1700
Data Index: 2486813 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.5297. Min Act: -0.1700
Data Index: 2994951 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.5297. Min Act: -0.1700
Data Index: 6240548 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4985. Min Act: -0.1700
Data Index: 491561 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4672. Min Act: -0.1700
Data Index: 6837225 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4360. Min Act: -0.1700
Data Index: 4904434 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4360. Min Act: -0.1700
Data Index: 7023446 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.4047. Min Act: -0.1700
Data Index: 4457025 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.3735. Min Act: -0.1700
Data Index: 6373378 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.3422. Min Act: -0.1700
Data Index: 251663 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8110. Min Range: -5.8110
Max Act: 5.3422. Min Act: -0.1700
Data Index: 159818 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19