Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1429. Min Range: -8.1429
Max Act: 8.1429. Min Act: -0.1700
Data Index: 2057288 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.9554. Min Act: -0.1700
Data Index: 4502621 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.9554. Min Act: -0.1700
Data Index: 3620318 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.6117. Min Act: -0.1700
Data Index: 1770671 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.6117. Min Act: -0.1700
Data Index: 7943886 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.6117. Min Act: -0.1700
Data Index: 3347830 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.5804. Min Act: -0.1700
Data Index: 6962373 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.5804. Min Act: -0.1700
Data Index: 1467010 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.5804. Min Act: -0.1700
Data Index: 7058248 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.5179. Min Act: -0.1700
Data Index: 1799355 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.4554. Min Act: -0.1700
Data Index: 4750261 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.3617. Min Act: -0.1700
Data Index: 3385268 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.3304. Min Act: -0.1700
Data Index: 8282160 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.3304. Min Act: -0.1700
Data Index: 4782628 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.3304. Min Act: -0.1700
Data Index: 3451018 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.3304. Min Act: -0.1700
Data Index: 4408507 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.2992. Min Act: -0.1700
Data Index: 5640196 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.2992. Min Act: -0.1700
Data Index: 4377306 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.3304. Min Act: -0.1700
Data Index: 6676993 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1429. Min Range: -8.1429
Max Act: 7.2679. Min Act: -0.1700
Data Index: 6574253 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19