Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1650 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2240. Min Range: -5.2240
Max Act: 5.2240. Min Act: -0.1700
Data Index: 7278656 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2240. Min Range: -5.2240
Max Act: 5.1928. Min Act: -0.1700
Data Index: 8809104 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2240. Min Range: -5.2240
Max Act: 5.1615. Min Act: -0.1700
Data Index: 107164 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2240. Min Range: -5.2240
Max Act: 5.0365. Min Act: -0.1700
Data Index: 6100417 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2240. Min Range: -5.2240
Max Act: 5.0678. Min Act: -0.1700
Data Index: 6832440 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2240. Min Range: -5.2240
Max Act: 5.0053. Min Act: -0.1700
Data Index: 7020293 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2240. Min Range: -5.2240
Max Act: 5.0053. Min Act: -0.1700
Data Index: 8553646 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2240. Min Range: -5.2240
Max Act: 4.9740. Min Act: -0.1700
Data Index: 6832264 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2240. Min Range: -5.2240
Max Act: 4.9740. Min Act: -0.1700
Data Index: 3376590 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2240. Min Range: -5.2240
Max Act: 5.0053. Min Act: -0.1700
Data Index: 2526896 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2240. Min Range: -5.2240
Max Act: 4.9740. Min Act: -0.1700
Data Index: 1570760 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2240. Min Range: -5.2240
Max Act: 4.9115. Min Act: -0.1700
Data Index: 419809 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2240. Min Range: -5.2240
Max Act: 4.9428. Min Act: -0.1700
Data Index: 4118677 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2240. Min Range: -5.2240
Max Act: 4.8803. Min Act: -0.1700
Data Index: 8291050 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2240. Min Range: -5.2240
Max Act: 4.8490. Min Act: -0.1700
Data Index: 1237602 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2240. Min Range: -5.2240
Max Act: 4.8490. Min Act: -0.1700
Data Index: 1990646 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2240. Min Range: -5.2240
Max Act: 4.8490. Min Act: -0.1700
Data Index: 1659454 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2240. Min Range: -5.2240
Max Act: 4.8803. Min Act: -0.1700
Data Index: 4513442 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2240. Min Range: -5.2240
Max Act: 4.8490. Min Act: -0.1700
Data Index: 6021973 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2240. Min Range: -5.2240
Max Act: 4.8178. Min Act: -0.1700
Data Index: 5284832 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19