Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1920 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.8050. Min Act: -0.1700
Data Index: 602610 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.8050. Min Act: -0.1700
Data Index: 6734476 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.6175. Min Act: -0.1700
Data Index: 3671495 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.4925. Min Act: -0.1697
Data Index: 2089166 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.4925. Min Act: -0.1699
Data Index: 3046514 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.4300. Min Act: -0.1698
Data Index: 2687147 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.4300. Min Act: -0.1700
Data Index: 5874690 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.3675. Min Act: -0.1700
Data Index: 5199656 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.3675. Min Act: -0.1696
Data Index: 1885160 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.2425. Min Act: -0.1700
Data Index: 3149163 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.3050. Min Act: -0.1700
Data Index: 6183464 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.2425. Min Act: -0.1700
Data Index: 2655473 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.2425. Min Act: -0.1698
Data Index: 3597229 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.2425. Min Act: -0.1700
Data Index: 5352072 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.1175. Min Act: -0.1700
Data Index: 1779093 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.3050. Min Act: -0.1700
Data Index: 5281073 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.3050. Min Act: -0.1700
Data Index: 6038978 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.1800. Min Act: -0.1700
Data Index: 4149117 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.1175. Min Act: -0.1700
Data Index: 5521682 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8050. Min Range: -9.8050
Max Act: 9.1800. Min Act: -0.1700
Data Index: 3251687 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19