Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3675 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8881. Min Act: -0.1700
Data Index: 6728143 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8569. Min Act: -0.1700
Data Index: 2985690 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8569. Min Act: -0.1700
Data Index: 3334824 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8256. Min Act: -0.1700
Data Index: 629213 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8256. Min Act: -0.1700
Data Index: 5267730 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8256. Min Act: -0.1700
Data Index: 4965454 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8256. Min Act: -0.1700
Data Index: 4612679 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8256. Min Act: -0.1700
Data Index: 8620328 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8256. Min Act: -0.1700
Data Index: 6746288 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8256. Min Act: -0.1700
Data Index: 4174870 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8256. Min Act: -0.1700
Data Index: 5934707 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8256. Min Act: -0.1700
Data Index: 3334825 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8256. Min Act: -0.1700
Data Index: 815828 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.8256. Min Act: -0.1700
Data Index: 5744243 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.7944. Min Act: -0.1700
Data Index: 1893773 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.7944. Min Act: -0.1700
Data Index: 4680916 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.7944. Min Act: -0.1700
Data Index: 1967385 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.7944. Min Act: -0.1700
Data Index: 4853060 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.7944. Min Act: -0.1700
Data Index: 2157882 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8881. Min Range: -4.8881
Max Act: 4.7944. Min Act: -0.1700
Data Index: 2387351 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19