Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1991 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3212. Min Range: -7.3212
Max Act: 7.3212. Min Act: -0.1700
Data Index: 2967933 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3212. Min Range: -7.3212
Max Act: 7.0400. Min Act: -0.1700
Data Index: 7963896 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.9775. Min Act: -0.1700
Data Index: 4135628 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.9150. Min Act: -0.1700
Data Index: 8529066 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.8837. Min Act: -0.1700
Data Index: 5393012 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.8837. Min Act: -0.1700
Data Index: 5987325 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.8837. Min Act: -0.1700
Data Index: 4832238 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.8837. Min Act: -0.1700
Data Index: 5482423 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.7900. Min Act: -0.1700
Data Index: 8526354 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.7900. Min Act: -0.1700
Data Index: 8744686 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.7900. Min Act: -0.1700
Data Index: 6894156 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.7587. Min Act: -0.1700
Data Index: 7352328 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.7587. Min Act: -0.1700
Data Index: 6319242 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.7275. Min Act: -0.1700
Data Index: 1422463 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.6650. Min Act: -0.1700
Data Index: 1442848 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.6337. Min Act: -0.1700
Data Index: 7205510 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.6337. Min Act: -0.1700
Data Index: 4611829 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.6025. Min Act: -0.1700
Data Index: 4832237 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.6025. Min Act: -0.1700
Data Index: 6143259 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3212. Min Range: -7.3212
Max Act: 6.5400. Min Act: -0.1700
Data Index: 2560391 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19