Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.8281. Min Act: -0.1700
Data Index: 1574176 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.7969. Min Act: -0.1700
Data Index: 4928077 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.7656. Min Act: -0.1700
Data Index: 4588085 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.7344. Min Act: -0.1700
Data Index: 10278 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.6719. Min Act: -0.1700
Data Index: 8089863 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.6719. Min Act: -0.1700
Data Index: 3605008 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.6406. Min Act: -0.1700
Data Index: 1399719 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.6094. Min Act: -0.1700
Data Index: 5393679 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.6406. Min Act: -0.1700
Data Index: 5148914 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.5781. Min Act: -0.1700
Data Index: 6244881 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.5781. Min Act: -0.1700
Data Index: 705850 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.5469. Min Act: -0.1700
Data Index: 58194 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.5469. Min Act: -0.1700
Data Index: 1544278 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.5469. Min Act: -0.1700
Data Index: 3454996 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.5469. Min Act: -0.1700
Data Index: 2954638 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.5156. Min Act: -0.1700
Data Index: 720582 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.5156. Min Act: -0.1700
Data Index: 254157 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.5156. Min Act: -0.1700
Data Index: 2628650 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.5469. Min Act: -0.1700
Data Index: 4250894 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8281. Min Range: -4.8281
Max Act: 4.5156. Min Act: -0.1700
Data Index: 5200624 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19