Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1252 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.4209. Min Act: -0.1700
Data Index: 2723064 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.3896. Min Act: -0.1700
Data Index: 697819 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.3584. Min Act: -0.1700
Data Index: 1097819 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2646. Min Act: -0.1700
Data Index: 8794104 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2959. Min Act: -0.1700
Data Index: 5168440 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2333. Min Act: -0.1699
Data Index: 8089041 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2021. Min Act: -0.1700
Data Index: 6319053 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2333. Min Act: -0.1700
Data Index: 3765687 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2021. Min Act: -0.1700
Data Index: 4359158 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2021. Min Act: -0.1699
Data Index: 307636 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2333. Min Act: -0.1699
Data Index: 5494951 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2021. Min Act: -0.1700
Data Index: 4165200 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2333. Min Act: -0.1700
Data Index: 4781341 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.1708. Min Act: -0.1700
Data Index: 5606365 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2021. Min Act: -0.1700
Data Index: 4348664 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2021. Min Act: -0.1700
Data Index: 363232 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2333. Min Act: -0.1700
Data Index: 520075 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.1708. Min Act: -0.1700
Data Index: 2115769 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2021. Min Act: -0.1700
Data Index: 2179232 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4209. Min Range: -4.4209
Max Act: 4.2021. Min Act: -0.1700
Data Index: 4517528 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19