Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3545 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.7962. Min Act: -0.1700
Data Index: 2936283 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.7650. Min Act: -0.1700
Data Index: 2080332 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.7025. Min Act: -0.1700
Data Index: 8760220 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.7337. Min Act: -0.1700
Data Index: 6999823 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.7337. Min Act: -0.1700
Data Index: 7825176 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.7025. Min Act: -0.1700
Data Index: 7608136 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.6712. Min Act: -0.1700
Data Index: 5688767 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.6087. Min Act: -0.1700
Data Index: 5943827 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.6087. Min Act: -0.1700
Data Index: 8026054 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.6087. Min Act: -0.1700
Data Index: 2015429 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.6087. Min Act: -0.1700
Data Index: 258484 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.6087. Min Act: -0.1700
Data Index: 1607116 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.5775. Min Act: -0.1700
Data Index: 8468328 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.5462. Min Act: -0.1700
Data Index: 5279955 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.5462. Min Act: -0.1700
Data Index: 3513450 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.4837. Min Act: -0.1700
Data Index: 8019250 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.4525. Min Act: -0.1700
Data Index: 7970870 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.4525. Min Act: -0.1700
Data Index: 3427398 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.4212. Min Act: -0.1700
Data Index: 7855479 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7962. Min Range: -5.7962
Max Act: 5.4212. Min Act: -0.1700
Data Index: 430242 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19