Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3241 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1965. Min Range: -5.1965
Max Act: 5.1965. Min Act: -0.1700
Data Index: 3546037 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1965. Min Range: -5.1965
Max Act: 5.1028. Min Act: -0.1700
Data Index: 5934237 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1965. Min Range: -5.1965
Max Act: 5.0090. Min Act: -0.1700
Data Index: 7697280 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.9778. Min Act: -0.1700
Data Index: 2522879 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.9465. Min Act: -0.1700
Data Index: 5270041 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.9465. Min Act: -0.1700
Data Index: 6447634 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.9153. Min Act: -0.1700
Data Index: 989134 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.9153. Min Act: -0.1700
Data Index: 1367005 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.8528. Min Act: -0.1700
Data Index: 915348 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.8528. Min Act: -0.1700
Data Index: 7581982 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.8528. Min Act: -0.1700
Data Index: 8801118 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.8215. Min Act: -0.1700
Data Index: 7882639 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.8528. Min Act: -0.1700
Data Index: 4291252 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.8215. Min Act: -0.1700
Data Index: 2958602 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.8215. Min Act: -0.1700
Data Index: 1885605 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.8215. Min Act: -0.1700
Data Index: 2115394 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.8215. Min Act: -0.1700
Data Index: 6224662 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.8215. Min Act: -0.1700
Data Index: 2153460 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.8215. Min Act: -0.1700
Data Index: 1307662 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1965. Min Range: -5.1965
Max Act: 4.7903. Min Act: -0.1700
Data Index: 7119021 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19