Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1538 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.5005. Min Act: -0.1700
Data Index: 2218057 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.4380. Min Act: -0.1700
Data Index: 3832839 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.4068. Min Act: -0.1700
Data Index: 3834264 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.3755. Min Act: -0.1700
Data Index: 6724661 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.3755. Min Act: -0.1700
Data Index: 882932 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.3755. Min Act: -0.1700
Data Index: 8154601 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.4068. Min Act: -0.1700
Data Index: 3275162 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.3443. Min Act: -0.1700
Data Index: 4069710 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.3443. Min Act: -0.1700
Data Index: 4315390 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.3443. Min Act: -0.1700
Data Index: 5899346 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.3443. Min Act: -0.1700
Data Index: 2846052 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.2818. Min Act: -0.1700
Data Index: 4508941 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.2818. Min Act: -0.1700
Data Index: 769667 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.3443. Min Act: -0.1700
Data Index: 6969741 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.3130. Min Act: -0.1700
Data Index: 5215973 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.2818. Min Act: -0.1700
Data Index: 2556217 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.2818. Min Act: -0.1700
Data Index: 4485960 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.2818. Min Act: -0.1700
Data Index: 2032321 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.2818. Min Act: -0.1700
Data Index: 416783 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5005. Min Range: -5.5005
Max Act: 5.2505. Min Act: -0.1700
Data Index: 6527809 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19