Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1482 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.4125. Min Act: -0.1700
Data Index: 849907 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.2875. Min Act: -0.1700
Data Index: 6750497 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.2250. Min Act: -0.1700
Data Index: 6183127 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.2250. Min Act: -0.1700
Data Index: 1162816 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.2562. Min Act: -0.1700
Data Index: 8424917 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1625. Min Act: -0.1700
Data Index: 8072827 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1625. Min Act: -0.1700
Data Index: 1899346 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1312. Min Act: -0.1700
Data Index: 418188 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1625. Min Act: -0.1700
Data Index: 6279794 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1625. Min Act: -0.1700
Data Index: 7788024 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1625. Min Act: -0.1700
Data Index: 7603277 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1625. Min Act: -0.1700
Data Index: 3198914 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1000. Min Act: -0.1700
Data Index: 7868339 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1000. Min Act: -0.1700
Data Index: 1399472 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1312. Min Act: -0.1700
Data Index: 3757508 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1625. Min Act: -0.1700
Data Index: 6213610 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1000. Min Act: -0.1700
Data Index: 7022732 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.0687. Min Act: -0.1700
Data Index: 6577335 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1000. Min Act: -0.1700
Data Index: 913592 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4125. Min Range: -5.4125
Max Act: 5.1000. Min Act: -0.1700
Data Index: 5342379 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19