Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4142 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2496. Min Range: -6.2496
Max Act: 6.2496. Min Act: -0.1700
Data Index: 6777389 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2496. Min Range: -6.2496
Max Act: 6.2183. Min Act: -0.1700
Data Index: 2057853 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2496. Min Range: -6.2496
Max Act: 6.1246. Min Act: -0.1700
Data Index: 5660523 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2496. Min Range: -6.2496
Max Act: 6.1246. Min Act: -0.1700
Data Index: 3551451 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2496. Min Range: -6.2496
Max Act: 6.0621. Min Act: -0.1700
Data Index: 4933633 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2496. Min Range: -6.2496
Max Act: 6.0621. Min Act: -0.1700
Data Index: 8787525 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2496. Min Range: -6.2496
Max Act: 6.0308. Min Act: -0.1700
Data Index: 8787527 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2496. Min Range: -6.2496
Max Act: 5.9996. Min Act: -0.1700
Data Index: 5687700 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2496. Min Range: -6.2496
Max Act: 6.0308. Min Act: -0.1700
Data Index: 4794955 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2496. Min Range: -6.2496
Max Act: 5.9683. Min Act: -0.1700
Data Index: 5993007 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2496. Min Range: -6.2496
Max Act: 5.9371. Min Act: -0.1700
Data Index: 5704219 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2496. Min Range: -6.2496
Max Act: 5.9683. Min Act: -0.1700
Data Index: 1459382 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2496. Min Range: -6.2496
Max Act: 5.9371. Min Act: -0.1700
Data Index: 674333 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2496. Min Range: -6.2496
Max Act: 5.9058. Min Act: -0.1700
Data Index: 1514625 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2496. Min Range: -6.2496
Max Act: 5.9371. Min Act: -0.1700
Data Index: 4968106 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2496. Min Range: -6.2496
Max Act: 5.9371. Min Act: -0.1700
Data Index: 3703579 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2496. Min Range: -6.2496
Max Act: 5.9058. Min Act: -0.1700
Data Index: 1786998 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2496. Min Range: -6.2496
Max Act: 5.9371. Min Act: -0.1700
Data Index: 1302268 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2496. Min Range: -6.2496
Max Act: 5.9058. Min Act: -0.1700
Data Index: 3389595 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2496. Min Range: -6.2496
Max Act: 5.8433. Min Act: -0.1700
Data Index: 928068 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19