Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1588 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3381. Min Range: -5.3381
Max Act: 5.3381. Min Act: -0.1700
Data Index: 8504545 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3381. Min Range: -5.3381
Max Act: 5.3381. Min Act: -0.1700
Data Index: 6059254 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3381. Min Range: -5.3381
Max Act: 5.1193. Min Act: -0.1700
Data Index: 3290906 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3381. Min Range: -5.3381
Max Act: 5.1193. Min Act: -0.1700
Data Index: 5950397 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3381. Min Range: -5.3381
Max Act: 5.1193. Min Act: -0.1700
Data Index: 8719496 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3381. Min Range: -5.3381
Max Act: 5.0881. Min Act: -0.1699
Data Index: 908844 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3381. Min Range: -5.3381
Max Act: 5.0568. Min Act: -0.1700
Data Index: 4857778 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3381. Min Range: -5.3381
Max Act: 5.0568. Min Act: -0.1700
Data Index: 3173947 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3381. Min Range: -5.3381
Max Act: 5.0568. Min Act: -0.1700
Data Index: 7460720 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3381. Min Range: -5.3381
Max Act: 5.0256. Min Act: -0.1700
Data Index: 1155629 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3381. Min Range: -5.3381
Max Act: 5.0256. Min Act: -0.1700
Data Index: 2132586 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3381. Min Range: -5.3381
Max Act: 4.9943. Min Act: -0.1700
Data Index: 6721981 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3381. Min Range: -5.3381
Max Act: 5.0256. Min Act: -0.1700
Data Index: 7334801 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3381. Min Range: -5.3381
Max Act: 4.9631. Min Act: -0.1700
Data Index: 995549 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3381. Min Range: -5.3381
Max Act: 4.9631. Min Act: -0.1700
Data Index: 5807697 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3381. Min Range: -5.3381
Max Act: 4.9943. Min Act: -0.1700
Data Index: 6462007 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3381. Min Range: -5.3381
Max Act: 4.9318. Min Act: -0.1700
Data Index: 2098972 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3381. Min Range: -5.3381
Max Act: 4.9631. Min Act: -0.1700
Data Index: 3929002 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3381. Min Range: -5.3381
Max Act: 4.9318. Min Act: -0.1700
Data Index: 2383198 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3381. Min Range: -5.3381
Max Act: 4.9318. Min Act: -0.1700
Data Index: 1254978 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19