Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 661 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.5658. Min Act: -0.1700
Data Index: 7766854 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.5345. Min Act: -0.1700
Data Index: 3538352 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.4405. Min Act: -0.1700
Data Index: 6427306 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.3622. Min Act: -0.1700
Data Index: 8652660 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2994. Min Act: -0.1700
Data Index: 3218792 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.3465. Min Act: -0.1700
Data Index: 2471642 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2837. Min Act: -0.1700
Data Index: 8052282 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2994. Min Act: -0.1700
Data Index: 3136251 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2837. Min Act: -0.1700
Data Index: 3842276 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2837. Min Act: -0.1700
Data Index: 4230867 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2680. Min Act: -0.1700
Data Index: 2823927 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2837. Min Act: -0.1700
Data Index: 3642025 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2680. Min Act: -0.1700
Data Index: 905627 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2680. Min Act: -0.1700
Data Index: 283471 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2523. Min Act: -0.1700
Data Index: 472255 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2366. Min Act: -0.1700
Data Index: 30536 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2051. Min Act: -0.1700
Data Index: 7221726 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2208. Min Act: -0.1700
Data Index: 4083016 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2051. Min Act: -0.1700
Data Index: 6017571 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5658. Min Range: -3.5658
Max Act: 3.2208. Min Act: -0.1700
Data Index: 1041215 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19