Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 650 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.2289. Min Act: -0.1700
Data Index: 5345530 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.1977. Min Act: -0.1700
Data Index: 5279658 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.1664. Min Act: -0.1700
Data Index: 232666 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.1039. Min Act: -0.1700
Data Index: 8467838 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.1352. Min Act: -0.1700
Data Index: 7341049 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0727. Min Act: -0.1700
Data Index: 4363568 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.1039. Min Act: -0.1700
Data Index: 3331165 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.1039. Min Act: -0.1700
Data Index: 3509818 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0727. Min Act: -0.1700
Data Index: 5857862 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0727. Min Act: -0.1700
Data Index: 3482040 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0414. Min Act: -0.1700
Data Index: 8621766 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0414. Min Act: -0.1700
Data Index: 7943781 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0102. Min Act: -0.1700
Data Index: 8361862 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0414. Min Act: -0.1700
Data Index: 8379575 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0414. Min Act: -0.1700
Data Index: 1095510 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0102. Min Act: -0.1700
Data Index: 8519239 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0727. Min Act: -0.1700
Data Index: 1004617 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0414. Min Act: -0.1700
Data Index: 641456 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0414. Min Act: -0.1700
Data Index: 5279295 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2289. Min Range: -5.2289
Max Act: 5.0414. Min Act: -0.1700
Data Index: 7341733 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19