Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.5538. Min Act: -0.1700
Data Index: 5883785 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.5225. Min Act: -0.1700
Data Index: 7330359 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.3975. Min Act: -0.1700
Data Index: 6121139 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.3663. Min Act: -0.1700
Data Index: 6427011 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.3350. Min Act: -0.1700
Data Index: 6186347 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.3038. Min Act: -0.1700
Data Index: 6649765 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.2725. Min Act: -0.1700
Data Index: 7603672 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.2100. Min Act: -0.1700
Data Index: 2636598 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.2413. Min Act: -0.1700
Data Index: 5117176 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.2100. Min Act: -0.1700
Data Index: 4142488 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.1788. Min Act: -0.1700
Data Index: 8439177 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.1788. Min Act: -0.1700
Data Index: 5561847 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.1163. Min Act: -0.1700
Data Index: 6268490 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.1475. Min Act: -0.1700
Data Index: 5505021 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.1163. Min Act: -0.1700
Data Index: 403017 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.1163. Min Act: -0.1700
Data Index: 2098539 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.0850. Min Act: -0.1700
Data Index: 3399832 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.0538. Min Act: -0.1700
Data Index: 2928656 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.0538. Min Act: -0.1700
Data Index: 3885568 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5538. Min Range: -5.5538
Max Act: 5.0538. Min Act: -0.1700
Data Index: 7698899 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19