Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3785 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.6013. Min Act: -0.1700
Data Index: 3451867 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.4882. Min Act: -0.1700
Data Index: 2843841 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.5044. Min Act: -0.1700
Data Index: 4016233 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.4882. Min Act: -0.1700
Data Index: 6306880 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.4720. Min Act: -0.1700
Data Index: 168536 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.4232. Min Act: -0.1700
Data Index: 3457167 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.4232. Min Act: -0.1700
Data Index: 766638 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.4232. Min Act: -0.1700
Data Index: 4011320 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.4069. Min Act: -0.1700
Data Index: 4156276 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.4069. Min Act: -0.1700
Data Index: 1657475 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.4069. Min Act: -0.1700
Data Index: 4410771 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.3742. Min Act: -0.1700
Data Index: 877831 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.3906. Min Act: -0.1700
Data Index: 6709298 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.3742. Min Act: -0.1700
Data Index: 5319747 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.3578. Min Act: -0.1700
Data Index: 4789684 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.3742. Min Act: -0.1700
Data Index: 5105109 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.3415. Min Act: -0.1700
Data Index: 1021241 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.3578. Min Act: -0.1700
Data Index: 3688894 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.3251. Min Act: -0.1700
Data Index: 274417 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6013. Min Range: -2.6013
Max Act: 2.3251. Min Act: -0.1700
Data Index: 427642 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19