Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1798 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1060. Min Range: -3.1060
Max Act: 3.1060. Min Act: -0.1700
Data Index: 7871196 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.9639. Min Act: -0.1700
Data Index: 2609781 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.9164. Min Act: -0.1700
Data Index: 535106 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8688. Min Act: -0.1700
Data Index: 8563703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8529. Min Act: -0.1700
Data Index: 836139 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8211. Min Act: -0.1700
Data Index: 65493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8211. Min Act: -0.1700
Data Index: 6392463 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8052. Min Act: -0.1700
Data Index: 1960520 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8052. Min Act: -0.1700
Data Index: 7123934 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7893. Min Act: -0.1700
Data Index: 3639492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7733. Min Act: -0.1700
Data Index: 5588659 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8052. Min Act: -0.1700
Data Index: 3626976 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7893. Min Act: -0.1700
Data Index: 2994103 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.8052. Min Act: -0.1700
Data Index: 4761295 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7893. Min Act: -0.1700
Data Index: 6527104 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7733. Min Act: -0.1700
Data Index: 3320941 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7574. Min Act: -0.1700
Data Index: 6315733 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7254. Min Act: -0.1700
Data Index: 4300277 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7414. Min Act: -0.1700
Data Index: 1720810 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1060. Min Range: -3.1060
Max Act: 2.7574. Min Act: -0.1700
Data Index: 6525110 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19