Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4023 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0827. Min Range: -4.0827
Max Act: 4.0827. Min Act: -0.1700
Data Index: 5154269 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9420. Min Act: -0.1700
Data Index: 4071197 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9264. Min Act: -0.1700
Data Index: 2982802 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9264. Min Act: -0.1700
Data Index: 3743477 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9107. Min Act: -0.1700
Data Index: 3012580 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9107. Min Act: -0.1700
Data Index: 2566580 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8951. Min Act: -0.1700
Data Index: 1777591 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8795. Min Act: -0.1700
Data Index: 1578958 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8795. Min Act: -0.1700
Data Index: 4839155 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8795. Min Act: -0.1700
Data Index: 4075019 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8482. Min Act: -0.1700
Data Index: 7187106 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8795. Min Act: -0.1700
Data Index: 8472775 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8638. Min Act: -0.1700
Data Index: 4622073 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8482. Min Act: -0.1700
Data Index: 4367995 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8169. Min Act: -0.1700
Data Index: 6061204 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8169. Min Act: -0.1700
Data Index: 5837001 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8169. Min Act: -0.1700
Data Index: 6726176 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.7856. Min Act: -0.1700
Data Index: 1411421 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.7856. Min Act: -0.1700
Data Index: 3579314 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.7856. Min Act: -0.1700
Data Index: 6111543 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19