Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1458 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.7011. Min Act: -0.1700
Data Index: 8756199 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.5136. Min Act: -0.1700
Data Index: 8252485 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.5136. Min Act: -0.1700
Data Index: 220210 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.4511. Min Act: -0.1700
Data Index: 635596 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.4823. Min Act: -0.1700
Data Index: 6697292 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.4198. Min Act: -0.1700
Data Index: 2722215 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.3886. Min Act: -0.1700
Data Index: 3628963 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.3573. Min Act: -0.1700
Data Index: 3138881 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.2636. Min Act: -0.1700
Data Index: 2273777 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.2323. Min Act: -0.1700
Data Index: 8615585 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.2323. Min Act: -0.1700
Data Index: 1803174 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.2011. Min Act: -0.1700
Data Index: 865209 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.2323. Min Act: -0.1700
Data Index: 6192929 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.2011. Min Act: -0.1700
Data Index: 2990277 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.2323. Min Act: -0.1700
Data Index: 1659809 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.2011. Min Act: -0.1700
Data Index: 1465818 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.2011. Min Act: -0.1700
Data Index: 683652 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.1698. Min Act: -0.1700
Data Index: 3527721 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.1386. Min Act: -0.1700
Data Index: 7226564 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7011. Min Range: -6.7011
Max Act: 6.1386. Min Act: -0.1700
Data Index: 548897 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19