Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 69 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.2866. Min Act: -0.1700
Data Index: 3613083 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.2554. Min Act: -0.1700
Data Index: 5039678 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.2554. Min Act: -0.1700
Data Index: 7963772 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.2554. Min Act: -0.1700
Data Index: 5624229 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.2241. Min Act: -0.1700
Data Index: 7125767 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.1616. Min Act: -0.1700
Data Index: 4054458 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.0991. Min Act: -0.1700
Data Index: 4054455 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.0991. Min Act: -0.1700
Data Index: 7690247 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.0678. Min Act: -0.1700
Data Index: 1186748 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.0678. Min Act: -0.1700
Data Index: 4365645 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.0366. Min Act: -0.1700
Data Index: 6017305 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.0678. Min Act: -0.1700
Data Index: 8660485 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.0366. Min Act: -0.1700
Data Index: 5336881 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.0053. Min Act: -0.1700
Data Index: 6209122 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.0053. Min Act: -0.1700
Data Index: 960575 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.0053. Min Act: -0.1700
Data Index: 7814989 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.0053. Min Act: -0.1700
Data Index: 7591582 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2866. Min Range: -4.2866
Max Act: 4.0053. Min Act: -0.1700
Data Index: 2659056 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2866. Min Range: -4.2866
Max Act: 3.9741. Min Act: -0.1700
Data Index: 6490326 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2866. Min Range: -4.2866
Max Act: 3.9428. Min Act: -0.1700
Data Index: 1024481 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19