Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5345. Min Range: -6.5345
Max Act: 6.5345. Min Act: -0.1700
Data Index: 7845660 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5345. Min Range: -6.5345
Max Act: 6.4095. Min Act: -0.1700
Data Index: 4603109 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5345. Min Range: -6.5345
Max Act: 6.2220. Min Act: -0.1700
Data Index: 6313310 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5345. Min Range: -6.5345
Max Act: 6.2220. Min Act: -0.1700
Data Index: 3323033 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5345. Min Range: -6.5345
Max Act: 6.1908. Min Act: -0.1700
Data Index: 5557634 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5345. Min Range: -6.5345
Max Act: 6.1595. Min Act: -0.1700
Data Index: 347115 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5345. Min Range: -6.5345
Max Act: 6.0658. Min Act: -0.1700
Data Index: 5078892 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5345. Min Range: -6.5345
Max Act: 6.0658. Min Act: -0.1700
Data Index: 4132355 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5345. Min Range: -6.5345
Max Act: 6.0658. Min Act: -0.1700
Data Index: 5557642 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5345. Min Range: -6.5345
Max Act: 6.0345. Min Act: -0.1700
Data Index: 4227987 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5345. Min Range: -6.5345
Max Act: 6.0033. Min Act: -0.1700
Data Index: 454153 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5345. Min Range: -6.5345
Max Act: 6.0033. Min Act: -0.1700
Data Index: 3453214 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5345. Min Range: -6.5345
Max Act: 5.9720. Min Act: -0.1700
Data Index: 7894136 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5345. Min Range: -6.5345
Max Act: 5.9095. Min Act: -0.1700
Data Index: 7337598 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5345. Min Range: -6.5345
Max Act: 5.9408. Min Act: -0.1700
Data Index: 2471235 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5345. Min Range: -6.5345
Max Act: 5.9408. Min Act: -0.1700
Data Index: 1309560 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5345. Min Range: -6.5345
Max Act: 5.9408. Min Act: -0.1700
Data Index: 7110127 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5345. Min Range: -6.5345
Max Act: 5.9408. Min Act: -0.1700
Data Index: 7110123 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5345. Min Range: -6.5345
Max Act: 5.9408. Min Act: -0.1700
Data Index: 5793353 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5345. Min Range: -6.5345
Max Act: 5.9095. Min Act: -0.1700
Data Index: 1736573 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19