Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 96 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.6766. Min Act: -0.1700
Data Index: 6259805 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.6453. Min Act: -0.1700
Data Index: 2804314 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.5827. Min Act: -0.1700
Data Index: 4812487 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.5827. Min Act: -0.1700
Data Index: 7412323 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.5200. Min Act: -0.1700
Data Index: 658714 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.5044. Min Act: -0.1700
Data Index: 2683937 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.4730. Min Act: -0.1700
Data Index: 1558665 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.4260. Min Act: -0.1700
Data Index: 5198294 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.4104. Min Act: -0.1700
Data Index: 1400928 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.4104. Min Act: -0.1700
Data Index: 7966801 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.3790. Min Act: -0.1700
Data Index: 76409 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.3633. Min Act: -0.1700
Data Index: 7918787 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.3790. Min Act: -0.1700
Data Index: 6787922 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.3319. Min Act: -0.1700
Data Index: 5638946 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.3319. Min Act: -0.1700
Data Index: 6008265 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.3319. Min Act: -0.1700
Data Index: 4055164 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.3163. Min Act: -0.1700
Data Index: 6350020 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.3006. Min Act: -0.1700
Data Index: 4542110 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.3163. Min Act: -0.1700
Data Index: 4854037 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6766. Min Range: -3.6766
Max Act: 3.2849. Min Act: -0.1700
Data Index: 2571800 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19