Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2121 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3658. Min Range: -9.3658
Max Act: 9.3658. Min Act: -0.1700
Data Index: 2829474 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3658. Min Range: -9.3658
Max Act: 9.0533. Min Act: -0.1700
Data Index: 5793790 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3658. Min Range: -9.3658
Max Act: 9.1158. Min Act: -0.1700
Data Index: 4198601 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.8658. Min Act: -0.1700
Data Index: 8780326 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.8033. Min Act: -0.1700
Data Index: 5118887 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.6783. Min Act: -0.1700
Data Index: 6676613 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.6783. Min Act: -0.1700
Data Index: 7330874 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.4908. Min Act: -0.1700
Data Index: 2807318 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.4908. Min Act: -0.1700
Data Index: 2982814 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.4908. Min Act: -0.1700
Data Index: 3950971 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.4595. Min Act: -0.1700
Data Index: 4100534 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.4283. Min Act: -0.1700
Data Index: 8564533 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.3658. Min Act: -0.1700
Data Index: 5379289 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.3345. Min Act: -0.1700
Data Index: 3343822 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.3345. Min Act: -0.1700
Data Index: 3595525 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.3345. Min Act: -0.1700
Data Index: 1704565 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.3033. Min Act: -0.1700
Data Index: 8162403 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.2720. Min Act: -0.1700
Data Index: 4343599 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.2720. Min Act: -0.1700
Data Index: 4734914 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3658. Min Range: -9.3658
Max Act: 8.2408. Min Act: -0.1700
Data Index: 359634 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19