Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 409 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1127. Min Range: -5.1127
Max Act: 5.1127. Min Act: -0.1700
Data Index: 2154132 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.9564. Min Act: -0.1700
Data Index: 6983554 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.9564. Min Act: -0.1700
Data Index: 2495993 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.8627. Min Act: -0.1700
Data Index: 8498862 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.8002. Min Act: -0.1700
Data Index: 3813192 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.8002. Min Act: -0.1700
Data Index: 4447030 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.8002. Min Act: -0.1700
Data Index: 838689 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7689. Min Act: -0.1700
Data Index: 5301547 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7689. Min Act: -0.1700
Data Index: 2800893 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7377. Min Act: -0.1700
Data Index: 8674433 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7377. Min Act: -0.1700
Data Index: 7525950 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7377. Min Act: -0.1700
Data Index: 8539951 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7377. Min Act: -0.1700
Data Index: 5786461 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7377. Min Act: -0.1700
Data Index: 8019685 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7064. Min Act: -0.1700
Data Index: 5392601 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7064. Min Act: -0.1700
Data Index: 7597162 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7064. Min Act: -0.1700
Data Index: 4678569 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7064. Min Act: -0.1700
Data Index: 5596569 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7064. Min Act: -0.1700
Data Index: 8016025 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1127. Min Range: -5.1127
Max Act: 4.7064. Min Act: -0.1700
Data Index: 8217273 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19