Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1864 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.9383. Min Act: -0.1700
Data Index: 4205811 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.6258. Min Act: -0.1700
Data Index: 3564677 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.4071. Min Act: -0.1700
Data Index: 6693605 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.3446. Min Act: -0.1700
Data Index: 4010536 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.3133. Min Act: -0.1700
Data Index: 1561355 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.2821. Min Act: -0.1700
Data Index: 7686355 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.1571. Min Act: -0.1700
Data Index: 4064646 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.1258. Min Act: -0.1700
Data Index: 833702 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.1258. Min Act: -0.1700
Data Index: 4890370 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.1571. Min Act: -0.1700
Data Index: 4637471 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.0633. Min Act: -0.1700
Data Index: 7826843 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.0633. Min Act: -0.1700
Data Index: 4662032 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.0633. Min Act: -0.1700
Data Index: 6157630 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.0321. Min Act: -0.1700
Data Index: 2078528 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.0321. Min Act: -0.1700
Data Index: 7103461 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.0321. Min Act: -0.1700
Data Index: 8044494 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.0008. Min Act: -0.1700
Data Index: 6213539 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9383. Min Range: -7.9383
Max Act: 6.9696. Min Act: -0.1700
Data Index: 7649276 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9383. Min Range: -7.9383
Max Act: 7.0008. Min Act: -0.1700
Data Index: 4627844 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9383. Min Range: -7.9383
Max Act: 6.9696. Min Act: -0.1700
Data Index: 4226096 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19