Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.5626. Min Act: -0.1700
Data Index: 6735813 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.6251. Min Act: -0.1700
Data Index: 2365406 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 3104064 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.5001. Min Act: -0.1700
Data Index: 5569467 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 7900009 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 6906146 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 8807938 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 8738131 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 4053318 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 8211531 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 5065147 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 7250245 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 5270769 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 1640299 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 7154178 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 5067302 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.4376. Min Act: -0.1700
Data Index: 3354578 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.3751. Min Act: -0.1700
Data Index: 4129767 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.3126. Min Act: -0.1700
Data Index: 2879577 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6251. Min Range: -8.6251
Max Act: 8.3751. Min Act: -0.1700
Data Index: 4947651 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19