Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1848 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.6579. Min Act: -0.1700
Data Index: 1631850 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.6109. Min Act: -0.1700
Data Index: 3168483 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.5953. Min Act: -0.1700
Data Index: 4024198 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.5483. Min Act: -0.1700
Data Index: 7203359 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.5170. Min Act: -0.1700
Data Index: 8751855 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.4857. Min Act: -0.1700
Data Index: 4117219 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.4857. Min Act: -0.1700
Data Index: 4650077 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.5013. Min Act: -0.1700
Data Index: 3995056 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.4857. Min Act: -0.1700
Data Index: 7038586 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.4857. Min Act: -0.1700
Data Index: 170434 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.4700. Min Act: -0.1700
Data Index: 3168484 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.4387. Min Act: -0.1700
Data Index: 5314684 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.4073. Min Act: -0.1700
Data Index: 7309766 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.4073. Min Act: -0.1700
Data Index: 4002970 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.3759. Min Act: -0.1700
Data Index: 851203 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.3603. Min Act: -0.1700
Data Index: 2341818 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.3289. Min Act: -0.1700
Data Index: 102026 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.3132. Min Act: -0.1700
Data Index: 4627425 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.3132. Min Act: -0.1700
Data Index: 102024 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6579. Min Range: -3.6579
Max Act: 3.2975. Min Act: -0.1700
Data Index: 1119221 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19