Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6886. Min Range: -8.6886
Max Act: 8.6886. Min Act: -0.1700
Data Index: 5822338 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6886. Min Range: -8.6886
Max Act: 8.5011. Min Act: -0.1700
Data Index: 1424459 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6886. Min Range: -8.6886
Max Act: 8.2511. Min Act: -0.1700
Data Index: 7848961 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6886. Min Range: -8.6886
Max Act: 8.1261. Min Act: -0.1700
Data Index: 7971232 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6886. Min Range: -8.6886
Max Act: 8.0011. Min Act: -0.1700
Data Index: 317632 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.9386. Min Act: -0.1700
Data Index: 1082799 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.9386. Min Act: -0.1700
Data Index: 5151799 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.9386. Min Act: -0.1700
Data Index: 5686158 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.9386. Min Act: -0.1700
Data Index: 4760721 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.8761. Min Act: -0.1700
Data Index: 1898265 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.8761. Min Act: -0.1700
Data Index: 154579 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.8761. Min Act: -0.1700
Data Index: 2851144 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.9386. Min Act: -0.1700
Data Index: 1448377 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.8761. Min Act: -0.1700
Data Index: 2285912 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.8761. Min Act: -0.1700
Data Index: 1704199 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.8136. Min Act: -0.1700
Data Index: 305368 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.8136. Min Act: -0.1700
Data Index: 3293722 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.7511. Min Act: -0.1700
Data Index: 2876033 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.8136. Min Act: -0.1700
Data Index: 2289000 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6886. Min Range: -8.6886
Max Act: 7.7511. Min Act: -0.1700
Data Index: 367612 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19