Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1808 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3374. Min Range: -5.3374
Max Act: 5.3374. Min Act: -0.1700
Data Index: 6890430 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3374. Min Range: -5.3374
Max Act: 5.1812. Min Act: -0.1700
Data Index: 82311 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3374. Min Range: -5.3374
Max Act: 5.1499. Min Act: -0.1700
Data Index: 4055177 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3374. Min Range: -5.3374
Max Act: 5.1187. Min Act: -0.1700
Data Index: 655044 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3374. Min Range: -5.3374
Max Act: 5.0874. Min Act: -0.1700
Data Index: 6267430 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3374. Min Range: -5.3374
Max Act: 5.0562. Min Act: -0.1700
Data Index: 6312554 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3374. Min Range: -5.3374
Max Act: 5.0562. Min Act: -0.1700
Data Index: 7891628 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3374. Min Range: -5.3374
Max Act: 5.0562. Min Act: -0.1700
Data Index: 6153538 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3374. Min Range: -5.3374
Max Act: 5.0874. Min Act: -0.1700
Data Index: 4829613 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3374. Min Range: -5.3374
Max Act: 5.0562. Min Act: -0.1700
Data Index: 1438144 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3374. Min Range: -5.3374
Max Act: 5.0249. Min Act: -0.1700
Data Index: 4330041 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3374. Min Range: -5.3374
Max Act: 5.0249. Min Act: -0.1700
Data Index: 4677914 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3374. Min Range: -5.3374
Max Act: 4.9937. Min Act: -0.1700
Data Index: 2916934 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3374. Min Range: -5.3374
Max Act: 4.9937. Min Act: -0.1700
Data Index: 842966 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3374. Min Range: -5.3374
Max Act: 4.9937. Min Act: -0.1700
Data Index: 6452685 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3374. Min Range: -5.3374
Max Act: 4.9624. Min Act: -0.1700
Data Index: 5552198 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3374. Min Range: -5.3374
Max Act: 4.9624. Min Act: -0.1700
Data Index: 8179735 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3374. Min Range: -5.3374
Max Act: 4.9624. Min Act: -0.1700
Data Index: 3516927 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3374. Min Range: -5.3374
Max Act: 4.9312. Min Act: -0.1700
Data Index: 7299409 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3374. Min Range: -5.3374
Max Act: 4.9312. Min Act: -0.1700
Data Index: 7010673 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19