Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 423 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7595. Min Range: -7.7595
Max Act: 7.7595. Min Act: -0.1700
Data Index: 7068157 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7595. Min Range: -7.7595
Max Act: 7.6657. Min Act: -0.1700
Data Index: 5225338 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7595. Min Range: -7.7595
Max Act: 7.3532. Min Act: -0.1700
Data Index: 3559409 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7595. Min Range: -7.7595
Max Act: 7.3220. Min Act: -0.1700
Data Index: 4853898 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7595. Min Range: -7.7595
Max Act: 7.3532. Min Act: -0.1700
Data Index: 7291821 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7595. Min Range: -7.7595
Max Act: 7.1970. Min Act: -0.1700
Data Index: 7132914 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7595. Min Range: -7.7595
Max Act: 7.1970. Min Act: -0.1700
Data Index: 6359648 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7595. Min Range: -7.7595
Max Act: 7.1657. Min Act: -0.1700
Data Index: 6359647 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7595. Min Range: -7.7595
Max Act: 7.1345. Min Act: -0.1700
Data Index: 4276091 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7595. Min Range: -7.7595
Max Act: 7.1032. Min Act: -0.1700
Data Index: 5871903 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7595. Min Range: -7.7595
Max Act: 6.9470. Min Act: -0.1700
Data Index: 7877209 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7595. Min Range: -7.7595
Max Act: 6.9157. Min Act: -0.1700
Data Index: 2305060 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7595. Min Range: -7.7595
Max Act: 6.9470. Min Act: -0.1700
Data Index: 455517 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7595. Min Range: -7.7595
Max Act: 6.9782. Min Act: -0.1700
Data Index: 6211995 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7595. Min Range: -7.7595
Max Act: 6.9157. Min Act: -0.1700
Data Index: 3256450 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7595. Min Range: -7.7595
Max Act: 6.9157. Min Act: -0.1700
Data Index: 2193386 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7595. Min Range: -7.7595
Max Act: 6.9157. Min Act: -0.1700
Data Index: 5182767 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7595. Min Range: -7.7595
Max Act: 6.9157. Min Act: -0.1700
Data Index: 8002831 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7595. Min Range: -7.7595
Max Act: 6.8845. Min Act: -0.1700
Data Index: 206525 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7595. Min Range: -7.7595
Max Act: 6.9157. Min Act: -0.1700
Data Index: 1343098 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19