Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4141 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1218. Min Range: -8.1218
Max Act: 8.1218. Min Act: -0.1700
Data Index: 6272907 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.8405. Min Act: -0.1700
Data Index: 838477 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.6530. Min Act: -0.1699
Data Index: 838471 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.6218. Min Act: -0.1700
Data Index: 5609101 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.6218. Min Act: -0.1700
Data Index: 6293271 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.5905. Min Act: -0.1700
Data Index: 4908528 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.5593. Min Act: -0.1700
Data Index: 1692244 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.5280. Min Act: -0.1700
Data Index: 2616172 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.4030. Min Act: -0.1700
Data Index: 5420478 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.3718. Min Act: -0.1700
Data Index: 4267735 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.3405. Min Act: -0.1700
Data Index: 838476 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.3405. Min Act: -0.1700
Data Index: 8599654 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.3093. Min Act: -0.1700
Data Index: 3768320 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.3093. Min Act: -0.1700
Data Index: 5705707 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.2780. Min Act: -0.1700
Data Index: 8350710 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.2780. Min Act: -0.1700
Data Index: 5828848 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.2780. Min Act: -0.1700
Data Index: 2234249 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.2468. Min Act: -0.1700
Data Index: 4601655 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.2468. Min Act: -0.1700
Data Index: 972805 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1218. Min Range: -8.1218
Max Act: 7.2468. Min Act: -0.1700
Data Index: 5453074 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19