Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.3160. Min Act: -0.1700
Data Index: 5143086 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.3160. Min Act: -0.1700
Data Index: 1216012 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.2848. Min Act: -0.1700
Data Index: 7338959 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.2535. Min Act: -0.1700
Data Index: 6336265 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.2535. Min Act: -0.1700
Data Index: 8662287 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.2223. Min Act: -0.1700
Data Index: 2169352 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.1598. Min Act: -0.1700
Data Index: 7369599 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.1910. Min Act: -0.1700
Data Index: 5946903 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.1910. Min Act: -0.1700
Data Index: 8515298 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.2223. Min Act: -0.1700
Data Index: 825628 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.1910. Min Act: -0.1700
Data Index: 8417017 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.1910. Min Act: -0.1700
Data Index: 6706602 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.1910. Min Act: -0.1700
Data Index: 5336697 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.1285. Min Act: -0.1700
Data Index: 397135 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.1910. Min Act: -0.1700
Data Index: 5333810 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.1598. Min Act: -0.1700
Data Index: 1441507 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.0973. Min Act: -0.1700
Data Index: 4959931 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.1285. Min Act: -0.1700
Data Index: 8022306 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.1285. Min Act: -0.1700
Data Index: 4180286 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3160. Min Range: -5.3160
Max Act: 5.0973. Min Act: -0.1700
Data Index: 6405660 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19