Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2334 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.3668. Min Act: -0.1700
Data Index: 8813980 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.3981. Min Act: -0.1700
Data Index: 2782025 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.3356. Min Act: -0.1700
Data Index: 2077901 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.1481. Min Act: -0.1700
Data Index: 7119251 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3981. Min Range: -5.3981
Max Act: 5.0543. Min Act: -0.1700
Data Index: 4070146 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.9918. Min Act: -0.1700
Data Index: 5522311 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.9918. Min Act: -0.1700
Data Index: 4312288 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.9918. Min Act: -0.1700
Data Index: 4253406 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.9918. Min Act: -0.1700
Data Index: 6171513 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.9606. Min Act: -0.1700
Data Index: 90403 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.9293. Min Act: -0.1700
Data Index: 8028516 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.8668. Min Act: -0.1700
Data Index: 4630032 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.8668. Min Act: -0.1700
Data Index: 43874 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.8668. Min Act: -0.1700
Data Index: 192936 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.8668. Min Act: -0.1700
Data Index: 2233789 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.8668. Min Act: -0.1700
Data Index: 4144157 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.8668. Min Act: -0.1700
Data Index: 338153 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.8356. Min Act: -0.1700
Data Index: 8036887 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.8356. Min Act: -0.1700
Data Index: 1950083 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3981. Min Range: -5.3981
Max Act: 4.8356. Min Act: -0.1700
Data Index: 2972296 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19