Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1044. Min Range: -6.1044
Max Act: 6.1044. Min Act: -0.1700
Data Index: 8525739 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1044. Min Range: -6.1044
Max Act: 6.0106. Min Act: -0.1700
Data Index: 5961245 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.9481. Min Act: -0.1700
Data Index: 8078205 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.9481. Min Act: -0.1700
Data Index: 1013716 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.9169. Min Act: -0.1700
Data Index: 1393252 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.9169. Min Act: -0.1700
Data Index: 115172 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.9169. Min Act: -0.1700
Data Index: 2677007 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.8856. Min Act: -0.1700
Data Index: 7183778 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.8856. Min Act: -0.1700
Data Index: 7401689 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.8544. Min Act: -0.1700
Data Index: 3329528 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.8544. Min Act: -0.1700
Data Index: 4554796 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.8544. Min Act: -0.1700
Data Index: 2166783 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.8231. Min Act: -0.1700
Data Index: 2125680 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.8231. Min Act: -0.1700
Data Index: 578021 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.8231. Min Act: -0.1700
Data Index: 3379942 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.8231. Min Act: -0.1700
Data Index: 836750 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.8231. Min Act: -0.1700
Data Index: 6443888 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.8231. Min Act: -0.1700
Data Index: 7932340 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.7919. Min Act: -0.1700
Data Index: 3218255 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1044. Min Range: -6.1044
Max Act: 5.7919. Min Act: -0.1700
Data Index: 2623408 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19