Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 754 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.7487. Min Act: -0.1700
Data Index: 381901 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.3112. Min Act: -0.1700
Data Index: 8317865 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.2487. Min Act: -0.1700
Data Index: 7447129 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.2175. Min Act: -0.1700
Data Index: 1484303 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.2175. Min Act: -0.1700
Data Index: 4430707 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.2175. Min Act: -0.1700
Data Index: 5498604 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.1550. Min Act: -0.1700
Data Index: 5895907 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.1550. Min Act: -0.1700
Data Index: 1289137 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.1550. Min Act: -0.1700
Data Index: 3709878 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.0925. Min Act: -0.1700
Data Index: 2770036 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.0612. Min Act: -0.1700
Data Index: 4809562 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.0612. Min Act: -0.1700
Data Index: 3381882 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.0300. Min Act: -0.1700
Data Index: 1219572 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.0612. Min Act: -0.1700
Data Index: 4855613 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.0300. Min Act: -0.1700
Data Index: 6296436 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.0612. Min Act: -0.1700
Data Index: 1317571 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7487. Min Range: -5.7487
Max Act: 5.0300. Min Act: -0.1700
Data Index: 7339585 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7487. Min Range: -5.7487
Max Act: 4.9675. Min Act: -0.1700
Data Index: 4846138 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7487. Min Range: -5.7487
Max Act: 4.9987. Min Act: -0.1700
Data Index: 5895908 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7487. Min Range: -5.7487
Max Act: 4.9987. Min Act: -0.1700
Data Index: 1132865 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19