Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1026 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.7658. Min Act: -0.1700
Data Index: 3550454 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.7346. Min Act: -0.1700
Data Index: 6055559 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.6721. Min Act: -0.1700
Data Index: 116556 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.6408. Min Act: -0.1700
Data Index: 5524223 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.6408. Min Act: -0.1700
Data Index: 2452158 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.6408. Min Act: -0.1700
Data Index: 8772118 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.6096. Min Act: -0.1700
Data Index: 1498462 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.5783. Min Act: -0.1700
Data Index: 2834516 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.6096. Min Act: -0.1700
Data Index: 7577082 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.5783. Min Act: -0.1700
Data Index: 1983283 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.5783. Min Act: -0.1700
Data Index: 5377658 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.5471. Min Act: -0.1700
Data Index: 5270833 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.5783. Min Act: -0.1700
Data Index: 6642545 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.5471. Min Act: -0.1700
Data Index: 856165 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.5471. Min Act: -0.1700
Data Index: 2410385 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.5158. Min Act: -0.1700
Data Index: 7147594 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.4846. Min Act: -0.1700
Data Index: 4415760 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.5158. Min Act: -0.1700
Data Index: 2780230 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.4846. Min Act: -0.1700
Data Index: 642515 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7658. Min Range: -6.7658
Max Act: 6.4533. Min Act: -0.1700
Data Index: 430023 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19