Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 808 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1851. Min Range: -4.1851
Max Act: 4.1851. Min Act: -0.1700
Data Index: 2302727 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1851. Min Range: -4.1851
Max Act: 4.0288. Min Act: -0.1700
Data Index: 3708996 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.9663. Min Act: -0.1700
Data Index: 4672314 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.9976. Min Act: -0.1700
Data Index: 8568012 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.9038. Min Act: -0.1700
Data Index: 2997993 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.8725. Min Act: -0.1700
Data Index: 8534142 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.8412. Min Act: -0.1700
Data Index: 7610289 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.8412. Min Act: -0.1700
Data Index: 5615973 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.8100. Min Act: -0.1700
Data Index: 385572 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.7474. Min Act: -0.1700
Data Index: 561324 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.8100. Min Act: -0.1700
Data Index: 576595 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.8100. Min Act: -0.1700
Data Index: 5599761 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.7787. Min Act: -0.1700
Data Index: 5280977 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.7787. Min Act: -0.1700
Data Index: 8015921 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.7787. Min Act: -0.1700
Data Index: 459815 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.8100. Min Act: -0.1700
Data Index: 3234937 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.7787. Min Act: -0.1700
Data Index: 559989 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.7787. Min Act: -0.1700
Data Index: 3914440 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.7474. Min Act: -0.1700
Data Index: 5599765 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1851. Min Range: -4.1851
Max Act: 3.7474. Min Act: -0.1700
Data Index: 4911060 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19