Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1218 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2078. Min Range: -5.2078
Max Act: 5.2078. Min Act: -0.1700
Data Index: 6266678 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2078. Min Range: -5.2078
Max Act: 5.2078. Min Act: -0.1700
Data Index: 5593191 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2078. Min Range: -5.2078
Max Act: 5.2078. Min Act: -0.1700
Data Index: 1652343 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2078. Min Range: -5.2078
Max Act: 5.1453. Min Act: -0.1700
Data Index: 1652344 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2078. Min Range: -5.2078
Max Act: 5.1141. Min Act: -0.1700
Data Index: 4804548 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2078. Min Range: -5.2078
Max Act: 5.0828. Min Act: -0.1700
Data Index: 58846 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2078. Min Range: -5.2078
Max Act: 5.0516. Min Act: -0.1700
Data Index: 2194151 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2078. Min Range: -5.2078
Max Act: 5.0516. Min Act: -0.1700
Data Index: 702577 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2078. Min Range: -5.2078
Max Act: 5.0203. Min Act: -0.1700
Data Index: 2955230 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2078. Min Range: -5.2078
Max Act: 4.9891. Min Act: -0.1700
Data Index: 1147928 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2078. Min Range: -5.2078
Max Act: 4.9891. Min Act: -0.1700
Data Index: 8097907 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2078. Min Range: -5.2078
Max Act: 4.9891. Min Act: -0.1700
Data Index: 4593145 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2078. Min Range: -5.2078
Max Act: 4.9578. Min Act: -0.1700
Data Index: 917225 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2078. Min Range: -5.2078
Max Act: 4.9578. Min Act: -0.1700
Data Index: 7940905 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2078. Min Range: -5.2078
Max Act: 4.9266. Min Act: -0.1700
Data Index: 2403146 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2078. Min Range: -5.2078
Max Act: 4.9578. Min Act: -0.1700
Data Index: 5300406 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2078. Min Range: -5.2078
Max Act: 4.9266. Min Act: -0.1700
Data Index: 2670136 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2078. Min Range: -5.2078
Max Act: 4.9266. Min Act: -0.1700
Data Index: 4014131 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2078. Min Range: -5.2078
Max Act: 4.9266. Min Act: -0.1700
Data Index: 1514773 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2078. Min Range: -5.2078
Max Act: 4.9266. Min Act: -0.1700
Data Index: 2366092 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19