Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1409 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3839. Min Range: -8.3839
Max Act: 8.3839. Min Act: -0.1700
Data Index: 290030 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.6651. Min Act: -0.1700
Data Index: 8248026 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.4776. Min Act: -0.1700
Data Index: 5884740 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.4776. Min Act: -0.1700
Data Index: 8248015 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.4151. Min Act: -0.1700
Data Index: 3622540 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.3214. Min Act: -0.1700
Data Index: 655763 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.3214. Min Act: -0.1700
Data Index: 3459338 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.2589. Min Act: -0.1700
Data Index: 3390737 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.2901. Min Act: -0.1700
Data Index: 2497801 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.2276. Min Act: -0.1700
Data Index: 4355895 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.1339. Min Act: -0.1700
Data Index: 3443822 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.1651. Min Act: -0.1700
Data Index: 6070385 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.1339. Min Act: -0.1700
Data Index: 1863895 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.1339. Min Act: -0.1700
Data Index: 628152 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.1651. Min Act: -0.1700
Data Index: 290029 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.0714. Min Act: -0.1700
Data Index: 7933428 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.0714. Min Act: -0.1700
Data Index: 8704078 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.1026. Min Act: -0.1700
Data Index: 8018973 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.0401. Min Act: -0.1700
Data Index: 1626506 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3839. Min Range: -8.3839
Max Act: 7.0089. Min Act: -0.1700
Data Index: 4462182 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19