Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3411 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.7783. Min Act: -0.1700
Data Index: 6331359 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.7783. Min Act: -0.1700
Data Index: 6011373 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.7471. Min Act: -0.1700
Data Index: 6523995 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.7471. Min Act: -0.1700
Data Index: 4300275 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.7158. Min Act: -0.1700
Data Index: 2732661 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.6533. Min Act: -0.1700
Data Index: 3399618 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.6533. Min Act: -0.1700
Data Index: 7732331 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.6533. Min Act: -0.1700
Data Index: 1513258 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.6846. Min Act: -0.1700
Data Index: 8150009 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.5908. Min Act: -0.1700
Data Index: 3854675 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4658. Min Act: -0.1700
Data Index: 788756 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4658. Min Act: -0.1700
Data Index: 4026013 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4658. Min Act: -0.1700
Data Index: 3179756 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4346. Min Act: -0.1700
Data Index: 778414 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4033. Min Act: -0.1700
Data Index: 2492771 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.4033. Min Act: -0.1700
Data Index: 8149976 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.3721. Min Act: -0.1700
Data Index: 172533 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.3408. Min Act: -0.1700
Data Index: 5292317 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.3408. Min Act: -0.1700
Data Index: 2635860 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7783. Min Range: -6.7783
Max Act: 6.3096. Min Act: -0.1700
Data Index: 6642147 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19