Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3908 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.4948. Min Act: -0.1700
Data Index: 485937 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.4636. Min Act: -0.1700
Data Index: 3585507 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.4323. Min Act: -0.1700
Data Index: 3585484 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.3386. Min Act: -0.1700
Data Index: 6041924 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.3386. Min Act: -0.1700
Data Index: 528606 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.3073. Min Act: -0.1700
Data Index: 3585489 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.2761. Min Act: -0.1700
Data Index: 6662133 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.2448. Min Act: -0.1700
Data Index: 3585509 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.2136. Min Act: -0.1700
Data Index: 1537368 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.1511. Min Act: -0.1700
Data Index: 5171553 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.1823. Min Act: -0.1700
Data Index: 7748704 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.1198. Min Act: -0.1700
Data Index: 6068526 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.1198. Min Act: -0.1700
Data Index: 8466179 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.1198. Min Act: -0.1700
Data Index: 4606536 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.1198. Min Act: -0.1700
Data Index: 977192 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.1198. Min Act: -0.1700
Data Index: 528614 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.0886. Min Act: -0.1700
Data Index: 16163 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.0573. Min Act: -0.1700
Data Index: 1645124 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.0261. Min Act: -0.1700
Data Index: 3585517 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4948. Min Range: -5.4948
Max Act: 5.0261. Min Act: -0.1700
Data Index: 3723669 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19