Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2510 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6996. Min Act: -0.1700
Data Index: 3791749 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6683. Min Act: -0.1700
Data Index: 4606421 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6683. Min Act: -0.1700
Data Index: 1178758 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6683. Min Act: -0.1700
Data Index: 5910390 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6683. Min Act: -0.1700
Data Index: 7684111 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6370. Min Act: -0.1700
Data Index: 367609 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6370. Min Act: -0.1700
Data Index: 3557484 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6370. Min Act: -0.1700
Data Index: 7711558 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6057. Min Act: -0.1700
Data Index: 5939567 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6057. Min Act: -0.1700
Data Index: 2671682 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6057. Min Act: -0.1700
Data Index: 8685652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6057. Min Act: -0.1700
Data Index: 8175364 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6057. Min Act: -0.1700
Data Index: 1273464 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6057. Min Act: -0.1700
Data Index: 2408884 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6057. Min Act: -0.1700
Data Index: 7354639 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6057. Min Act: -0.1700
Data Index: 5175884 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6057. Min Act: -0.1700
Data Index: 1077372 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6057. Min Act: -0.1700
Data Index: 4044320 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6057. Min Act: -0.1700
Data Index: 3809597 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5744. Min Act: -0.1700
Data Index: 1321896 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19