Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2793 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0037. Min Range: -5.0037
Max Act: 5.0037. Min Act: -0.1700
Data Index: 7116008 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.9724. Min Act: -0.1700
Data Index: 1998032 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.9412. Min Act: -0.1700
Data Index: 5732380 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.9412. Min Act: -0.1700
Data Index: 1287021 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.9412. Min Act: -0.1700
Data Index: 3948250 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.9099. Min Act: -0.1700
Data Index: 2794719 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.9099. Min Act: -0.1700
Data Index: 6183205 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.8787. Min Act: -0.1700
Data Index: 6465891 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.8474. Min Act: -0.1700
Data Index: 3618202 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.8474. Min Act: -0.1700
Data Index: 6984860 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.8162. Min Act: -0.1700
Data Index: 4459665 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.8474. Min Act: -0.1700
Data Index: 4159844 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.8162. Min Act: -0.1700
Data Index: 1927372 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.8162. Min Act: -0.1700
Data Index: 4170618 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.8162. Min Act: -0.1700
Data Index: 7166961 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.8162. Min Act: -0.1700
Data Index: 1693676 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.8162. Min Act: -0.1700
Data Index: 416550 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.7537. Min Act: -0.1700
Data Index: 4953943 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.7537. Min Act: -0.1700
Data Index: 6194901 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0037. Min Range: -5.0037
Max Act: 4.7537. Min Act: -0.1700
Data Index: 1156346 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19