Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4574 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.8015. Min Act: -0.1700
Data Index: 1816277 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.8015. Min Act: -0.1700
Data Index: 3331300 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7377. Min Act: -0.1700
Data Index: 1225390 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7537. Min Act: -0.1700
Data Index: 2113220 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7217. Min Act: -0.1700
Data Index: 1566187 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.7217. Min Act: -0.1700
Data Index: 7751360 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6737. Min Act: -0.1700
Data Index: 2714832 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6897. Min Act: -0.1700
Data Index: 4474121 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6737. Min Act: -0.1700
Data Index: 6767755 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6577. Min Act: -0.1700
Data Index: 8139516 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6577. Min Act: -0.1700
Data Index: 8285253 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6416. Min Act: -0.1700
Data Index: 1525982 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6256. Min Act: -0.1700
Data Index: 2376690 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6256. Min Act: -0.1700
Data Index: 7878642 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6416. Min Act: -0.1700
Data Index: 8240976 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6256. Min Act: -0.1700
Data Index: 6255882 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.6095. Min Act: -0.1700
Data Index: 720378 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.5934. Min Act: -0.1700
Data Index: 6378480 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.5773. Min Act: -0.1700
Data Index: 120392 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8015. Min Range: -2.8015
Max Act: 2.5773. Min Act: -0.1700
Data Index: 1592434 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19