Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1456 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0428. Min Range: -6.0428
Max Act: 6.0428. Min Act: -0.1700
Data Index: 1558968 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.9803. Min Act: -0.1700
Data Index: 1760191 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.7615. Min Act: -0.1700
Data Index: 8006152 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.7615. Min Act: -0.1700
Data Index: 6053795 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6678. Min Act: -0.1700
Data Index: 3306141 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6990. Min Act: -0.1700
Data Index: 6293038 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6990. Min Act: -0.1700
Data Index: 6423437 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6990. Min Act: -0.1700
Data Index: 8006170 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6990. Min Act: -0.1700
Data Index: 3306148 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6678. Min Act: -0.1700
Data Index: 7144792 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6990. Min Act: -0.1700
Data Index: 4883832 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6678. Min Act: -0.1700
Data Index: 4729264 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6678. Min Act: -0.1700
Data Index: 746264 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6678. Min Act: -0.1700
Data Index: 7190773 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6053. Min Act: -0.1700
Data Index: 1760203 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6365. Min Act: -0.1700
Data Index: 5020234 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6365. Min Act: -0.1700
Data Index: 7144789 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6365. Min Act: -0.1700
Data Index: 3306143 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6053. Min Act: -0.1700
Data Index: 1760195 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0428. Min Range: -6.0428
Max Act: 5.6365. Min Act: -0.1700
Data Index: 6053799 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19