Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 686 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0065. Min Range: -2.0065
Max Act: 2.0065. Min Act: -0.1700
Data Index: 2603913 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9896. Min Act: -0.1700
Data Index: 6804760 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9727. Min Act: -0.1700
Data Index: 8349306 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9727. Min Act: -0.1700
Data Index: 759575 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9727. Min Act: -0.1700
Data Index: 1843474 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9558. Min Act: -0.1700
Data Index: 7876586 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9558. Min Act: -0.1700
Data Index: 3028321 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9558. Min Act: -0.1700
Data Index: 7127465 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9388. Min Act: -0.1700
Data Index: 2426074 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9388. Min Act: -0.1700
Data Index: 210444 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9388. Min Act: -0.1700
Data Index: 2863547 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9388. Min Act: -0.1700
Data Index: 3340170 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9388. Min Act: -0.1700
Data Index: 3628091 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9388. Min Act: -0.1699
Data Index: 4127116 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9388. Min Act: -0.1700
Data Index: 7769630 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9388. Min Act: -0.1700
Data Index: 4355233 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9388. Min Act: -0.1700
Data Index: 5387824 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9047. Min Act: -0.1698
Data Index: 3645567 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9218. Min Act: -0.1699
Data Index: 1129687 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0065. Min Range: -2.0065
Max Act: 1.9218. Min Act: -0.1700
Data Index: 4066247 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19