Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 53 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1002. Min Range: -5.1002
Max Act: 5.1002. Min Act: -0.1700
Data Index: 2246972 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1002. Min Range: -5.1002
Max Act: 5.0377. Min Act: -0.1700
Data Index: 5029708 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1002. Min Range: -5.1002
Max Act: 5.0064. Min Act: -0.1700
Data Index: 3001017 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.8814. Min Act: -0.1700
Data Index: 2554352 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.8502. Min Act: -0.1700
Data Index: 8350765 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.8502. Min Act: -0.1700
Data Index: 46365 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.8502. Min Act: -0.1700
Data Index: 3622375 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7877. Min Act: -0.1700
Data Index: 3040360 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7877. Min Act: -0.1700
Data Index: 649140 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7877. Min Act: -0.1700
Data Index: 8305255 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7877. Min Act: -0.1700
Data Index: 157856 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7252. Min Act: -0.1700
Data Index: 2315164 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7877. Min Act: -0.1700
Data Index: 3268994 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7252. Min Act: -0.1700
Data Index: 3650117 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7564. Min Act: -0.1700
Data Index: 100831 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7252. Min Act: -0.1700
Data Index: 4501182 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7252. Min Act: -0.1700
Data Index: 4762192 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7252. Min Act: -0.1700
Data Index: 3897718 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7252. Min Act: -0.1700
Data Index: 5454856 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1002. Min Range: -5.1002
Max Act: 4.7252. Min Act: -0.1700
Data Index: 1462398 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19