Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5218 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1793. Min Range: -7.1793
Max Act: 7.1793. Min Act: -0.1700
Data Index: 7777699 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1793. Min Range: -7.1793
Max Act: 7.1481. Min Act: -0.1700
Data Index: 294971 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1793. Min Range: -7.1793
Max Act: 7.0231. Min Act: -0.1700
Data Index: 1541839 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1793. Min Range: -7.1793
Max Act: 7.0543. Min Act: -0.1700
Data Index: 3238134 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.9918. Min Act: -0.1700
Data Index: 3509592 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8981. Min Act: -0.1700
Data Index: 4881167 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8981. Min Act: -0.1700
Data Index: 2484152 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8668. Min Act: -0.1700
Data Index: 6881727 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8981. Min Act: -0.1700
Data Index: 3311550 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8981. Min Act: -0.1700
Data Index: 6648277 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8981. Min Act: -0.1700
Data Index: 6785418 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8356. Min Act: -0.1700
Data Index: 7311355 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8356. Min Act: -0.1700
Data Index: 110759 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8668. Min Act: -0.1700
Data Index: 7301187 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8668. Min Act: -0.1700
Data Index: 392839 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8356. Min Act: -0.1700
Data Index: 2852975 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8356. Min Act: -0.1700
Data Index: 606849 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8356. Min Act: -0.1700
Data Index: 4819235 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.8043. Min Act: -0.1700
Data Index: 3026465 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1793. Min Range: -7.1793
Max Act: 6.7731. Min Act: -0.1700
Data Index: 7739283 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19