Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2754 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2613. Min Range: -5.2613
Max Act: 5.2613. Min Act: -0.1700
Data Index: 5008942 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2613. Min Range: -5.2613
Max Act: 5.1363. Min Act: -0.1700
Data Index: 1015394 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2613. Min Range: -5.2613
Max Act: 4.4800. Min Act: -0.1700
Data Index: 7554392 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2613. Min Range: -5.2613
Max Act: 4.4800. Min Act: -0.1700
Data Index: 2606988 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2613. Min Range: -5.2613
Max Act: 4.3237. Min Act: -0.1700
Data Index: 4468596 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2613. Min Range: -5.2613
Max Act: 4.1987. Min Act: -0.1700
Data Index: 4821223 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2613. Min Range: -5.2613
Max Act: 4.1362. Min Act: -0.1700
Data Index: 2741739 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2613. Min Range: -5.2613
Max Act: 4.1675. Min Act: -0.1700
Data Index: 7094605 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2613. Min Range: -5.2613
Max Act: 4.0737. Min Act: -0.1700
Data Index: 4641713 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2613. Min Range: -5.2613
Max Act: 3.8861. Min Act: -0.1700
Data Index: 4364628 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2613. Min Range: -5.2613
Max Act: 3.9487. Min Act: -0.1700
Data Index: 7717697 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2613. Min Range: -5.2613
Max Act: 3.9174. Min Act: -0.1700
Data Index: 8139179 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2613. Min Range: -5.2613
Max Act: 3.9174. Min Act: -0.1700
Data Index: 3299647 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2613. Min Range: -5.2613
Max Act: 3.8861. Min Act: -0.1700
Data Index: 3719373 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2613. Min Range: -5.2613
Max Act: 3.8861. Min Act: -0.1700
Data Index: 438174 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2613. Min Range: -5.2613
Max Act: 3.8392. Min Act: -0.1700
Data Index: 1280363 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2613. Min Range: -5.2613
Max Act: 3.8705. Min Act: -0.1700
Data Index: 4394734 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2613. Min Range: -5.2613
Max Act: 3.8705. Min Act: -0.1700
Data Index: 6243486 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2613. Min Range: -5.2613
Max Act: 3.8549. Min Act: -0.1700
Data Index: 4917145 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2613. Min Range: -5.2613
Max Act: 3.8861. Min Act: -0.1700
Data Index: 7401027 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19