Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1135 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.8935. Min Act: -0.1700
Data Index: 115993 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.8458. Min Act: -0.1700
Data Index: 7698913 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.7981. Min Act: -0.1700
Data Index: 2981916 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.7343. Min Act: -0.1700
Data Index: 2842292 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.7023. Min Act: -0.1700
Data Index: 1254951 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6703. Min Act: -0.1700
Data Index: 4090617 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6382. Min Act: -0.1700
Data Index: 3670182 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6222. Min Act: -0.1700
Data Index: 7683183 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6543. Min Act: -0.1700
Data Index: 8628877 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6382. Min Act: -0.1700
Data Index: 8528194 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6382. Min Act: -0.1700
Data Index: 8046386 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6222. Min Act: -0.1700
Data Index: 6090385 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6222. Min Act: -0.1700
Data Index: 4338846 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6222. Min Act: -0.1700
Data Index: 7756068 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6061. Min Act: -0.1700
Data Index: 4755458 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6222. Min Act: -0.1700
Data Index: 7380928 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6061. Min Act: -0.1700
Data Index: 7925072 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.5900. Min Act: -0.1700
Data Index: 460732 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.5900. Min Act: -0.1700
Data Index: 6977304 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8935. Min Range: -2.8935
Max Act: 2.6061. Min Act: -0.1700
Data Index: 1660861 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19