Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3245 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3326. Min Range: -6.3326
Max Act: 6.3326. Min Act: -0.1700
Data Index: 2019443 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3326. Min Range: -6.3326
Max Act: 6.2701. Min Act: -0.1700
Data Index: 967633 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3326. Min Range: -6.3326
Max Act: 6.0514. Min Act: -0.1700
Data Index: 4010830 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3326. Min Range: -6.3326
Max Act: 6.0514. Min Act: -0.1700
Data Index: 5841576 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.9576. Min Act: -0.1700
Data Index: 2449772 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.9576. Min Act: -0.1700
Data Index: 7719588 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.9264. Min Act: -0.1700
Data Index: 2888005 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.9576. Min Act: -0.1700
Data Index: 7144721 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.8951. Min Act: -0.1700
Data Index: 3592225 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.8639. Min Act: -0.1700
Data Index: 5289483 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.8326. Min Act: -0.1700
Data Index: 8688222 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.8326. Min Act: -0.1700
Data Index: 4362305 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.8014. Min Act: -0.1700
Data Index: 4757461 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.7701. Min Act: -0.1700
Data Index: 3325745 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.7389. Min Act: -0.1700
Data Index: 4119527 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.7076. Min Act: -0.1700
Data Index: 6091556 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.6451. Min Act: -0.1700
Data Index: 5329905 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.6451. Min Act: -0.1700
Data Index: 5446562 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.6451. Min Act: -0.1700
Data Index: 5264407 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3326. Min Range: -6.3326
Max Act: 5.6451. Min Act: -0.1700
Data Index: 4782575 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19