Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1570 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.3856. Min Act: -0.1700
Data Index: 4926129 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.3231. Min Act: -0.1700
Data Index: 651757 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.2918. Min Act: -0.1700
Data Index: 2741190 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.2293. Min Act: -0.1700
Data Index: 1189103 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.1668. Min Act: -0.1700
Data Index: 7913183 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.1668. Min Act: -0.1700
Data Index: 7216307 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.1356. Min Act: -0.1700
Data Index: 2477469 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.1043. Min Act: -0.1700
Data Index: 1046636 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.0418. Min Act: -0.1700
Data Index: 3375192 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.0731. Min Act: -0.1700
Data Index: 4985315 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.0418. Min Act: -0.1700
Data Index: 1044455 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.0418. Min Act: -0.1700
Data Index: 7096828 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.0106. Min Act: -0.1700
Data Index: 8695051 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3856. Min Range: -5.3856
Max Act: 5.0106. Min Act: -0.1700
Data Index: 3274029 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3856. Min Range: -5.3856
Max Act: 4.9793. Min Act: -0.1700
Data Index: 5409308 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3856. Min Range: -5.3856
Max Act: 4.9481. Min Act: -0.1700
Data Index: 3839244 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3856. Min Range: -5.3856
Max Act: 4.9168. Min Act: -0.1700
Data Index: 5765220 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3856. Min Range: -5.3856
Max Act: 4.9168. Min Act: -0.1700
Data Index: 3598669 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3856. Min Range: -5.3856
Max Act: 4.8856. Min Act: -0.1700
Data Index: 3173726 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3856. Min Range: -5.3856
Max Act: 4.9168. Min Act: -0.1700
Data Index: 3771756 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19