Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5460 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.7491. Min Act: -0.1700
Data Index: 5953085 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.7491. Min Act: -0.1700
Data Index: 5953084 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.7491. Min Act: -0.1700
Data Index: 3898711 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.6866. Min Act: -0.1700
Data Index: 2193606 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.6241. Min Act: -0.1700
Data Index: 3641837 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.6241. Min Act: -0.1700
Data Index: 3763948 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.5616. Min Act: -0.1700
Data Index: 1536139 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.5616. Min Act: -0.1700
Data Index: 3634854 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.6241. Min Act: -0.1700
Data Index: 3890444 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.6241. Min Act: -0.1700
Data Index: 5782266 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.4991. Min Act: -0.1700
Data Index: 1536142 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.4366. Min Act: -0.1700
Data Index: 6584427 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.4991. Min Act: -0.1699
Data Index: 1536137 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.4991. Min Act: -0.1700
Data Index: 3890446 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.4991. Min Act: -0.1700
Data Index: 4346208 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.4366. Min Act: -0.1700
Data Index: 2635318 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.3741. Min Act: -0.1700
Data Index: 1536140 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.4366. Min Act: -0.1700
Data Index: 6928878 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.4991. Min Act: -0.1700
Data Index: 3466334 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7491. Min Range: -8.7491
Max Act: 8.4366. Min Act: -0.1700
Data Index: 3709645 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19