Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1155 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9813. Min Act: -0.1700
Data Index: 4791859 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9813. Min Act: -0.1700
Data Index: 3524607 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9813. Min Act: -0.1700
Data Index: 1343874 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9813. Min Act: -0.1700
Data Index: 2313430 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9655. Min Act: -0.1700
Data Index: 5558783 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9655. Min Act: -0.1700
Data Index: 371368 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9655. Min Act: -0.1700
Data Index: 2639590 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9496. Min Act: -0.1700
Data Index: 7157837 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9496. Min Act: -0.1700
Data Index: 3869088 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9496. Min Act: -0.1700
Data Index: 6571657 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9338. Min Act: -0.1700
Data Index: 1163535 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9338. Min Act: -0.1700
Data Index: 754767 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9338. Min Act: -0.1700
Data Index: 3673675 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9338. Min Act: -0.1700
Data Index: 1535638 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9338. Min Act: -0.1700
Data Index: 384774 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9338. Min Act: -0.1700
Data Index: 242410 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9180. Min Act: -0.1700
Data Index: 3916342 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9180. Min Act: -0.1700
Data Index: 4717522 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9180. Min Act: -0.1700
Data Index: 783101 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9813. Min Range: -2.9813
Max Act: 2.9180. Min Act: -0.1700
Data Index: 235623 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19