Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5658. Min Range: -8.5658
Max Act: 8.5658. Min Act: -0.1700
Data Index: 956714 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5658. Min Range: -8.5658
Max Act: 8.1908. Min Act: -0.1700
Data Index: 317434 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5658. Min Range: -8.5658
Max Act: 8.0658. Min Act: -0.1700
Data Index: 45742 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5658. Min Range: -8.5658
Max Act: 8.0033. Min Act: -0.1700
Data Index: 4445505 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.9408. Min Act: -0.1700
Data Index: 7110458 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.9408. Min Act: -0.1700
Data Index: 2629349 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.8783. Min Act: -0.1700
Data Index: 5489355 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.7533. Min Act: -0.1700
Data Index: 4255597 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.7220. Min Act: -0.1700
Data Index: 4288898 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.7220. Min Act: -0.1700
Data Index: 478311 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.6908. Min Act: -0.1700
Data Index: 8243988 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.5658. Min Act: -0.1700
Data Index: 2511697 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.5658. Min Act: -0.1700
Data Index: 3138722 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.5658. Min Act: -0.1700
Data Index: 7476751 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.5658. Min Act: -0.1700
Data Index: 39515 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.6283. Min Act: -0.1700
Data Index: 3243830 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.5033. Min Act: -0.1700
Data Index: 3115407 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.4720. Min Act: -0.1700
Data Index: 2347469 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.5345. Min Act: -0.1700
Data Index: 1650806 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5658. Min Range: -8.5658
Max Act: 7.4408. Min Act: -0.1700
Data Index: 5817835 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19