Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.4253. Min Act: -0.1700
Data Index: 3578489 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.3941. Min Act: -0.1700
Data Index: 2349847 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.3628. Min Act: -0.1700
Data Index: 4126703 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.3316. Min Act: -0.1700
Data Index: 1876674 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.3316. Min Act: -0.1700
Data Index: 1301753 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.3003. Min Act: -0.1700
Data Index: 7026916 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.3003. Min Act: -0.1700
Data Index: 2785277 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.3003. Min Act: -0.1700
Data Index: 2669300 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.3003. Min Act: -0.1700
Data Index: 683194 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.2691. Min Act: -0.1700
Data Index: 6836119 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.2691. Min Act: -0.1700
Data Index: 6581623 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.2691. Min Act: -0.1700
Data Index: 5990595 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.2691. Min Act: -0.1700
Data Index: 7460879 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.2066. Min Act: -0.1700
Data Index: 2221786 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.2378. Min Act: -0.1700
Data Index: 6585251 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.2378. Min Act: -0.1700
Data Index: 4870866 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.2378. Min Act: -0.1700
Data Index: 7460877 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.2066. Min Act: -0.1700
Data Index: 3527427 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.1753. Min Act: -0.1700
Data Index: 1920596 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4253. Min Range: -5.4253
Max Act: 5.1441. Min Act: -0.1700
Data Index: 6649641 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19