Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3222 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1796. Min Range: -5.1796
Max Act: 5.1796. Min Act: -0.1700
Data Index: 4540603 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1796. Min Range: -5.1796
Max Act: 5.1171. Min Act: -0.1700
Data Index: 439202 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.9608. Min Act: -0.1700
Data Index: 4477692 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.9608. Min Act: -0.1700
Data Index: 3197108 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.8983. Min Act: -0.1700
Data Index: 6041453 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.8358. Min Act: -0.1700
Data Index: 7637585 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.8358. Min Act: -0.1700
Data Index: 2075415 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.8358. Min Act: -0.1700
Data Index: 6136378 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.7733. Min Act: -0.1700
Data Index: 290325 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.7733. Min Act: -0.1700
Data Index: 2775069 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.7733. Min Act: -0.1700
Data Index: 408900 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.8046. Min Act: -0.1700
Data Index: 3170560 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.7421. Min Act: -0.1700
Data Index: 2526906 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.7421. Min Act: -0.1700
Data Index: 3017011 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.7733. Min Act: -0.1700
Data Index: 991222 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.7421. Min Act: -0.1700
Data Index: 919238 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.7421. Min Act: -0.1700
Data Index: 350710 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.7421. Min Act: -0.1700
Data Index: 2869015 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.7108. Min Act: -0.1700
Data Index: 2053991 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1796. Min Range: -5.1796
Max Act: 4.7421. Min Act: -0.1700
Data Index: 3935744 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19