Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3897 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4668. Min Range: -5.4668
Max Act: 5.4668. Min Act: -0.1700
Data Index: 8613463 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4668. Min Range: -5.4668
Max Act: 5.3731. Min Act: -0.1700
Data Index: 256435 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4668. Min Range: -5.4668
Max Act: 5.0293. Min Act: -0.1700
Data Index: 7282166 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4668. Min Range: -5.4668
Max Act: 5.0293. Min Act: -0.1700
Data Index: 5625110 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.9668. Min Act: -0.1700
Data Index: 4718625 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.8418. Min Act: -0.1700
Data Index: 7849144 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.7793. Min Act: -0.1700
Data Index: 218503 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.7481. Min Act: -0.1700
Data Index: 8672819 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.6856. Min Act: -0.1700
Data Index: 2415120 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.7168. Min Act: -0.1700
Data Index: 279748 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.7168. Min Act: -0.1700
Data Index: 852531 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.6856. Min Act: -0.1700
Data Index: 3980430 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.7481. Min Act: -0.1700
Data Index: 169003 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.7168. Min Act: -0.1700
Data Index: 249798 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.6856. Min Act: -0.1700
Data Index: 178955 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.7168. Min Act: -0.1700
Data Index: 2152624 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.7793. Min Act: -0.1700
Data Index: 5692502 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.7168. Min Act: -0.1700
Data Index: 2440847 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.7168. Min Act: -0.1700
Data Index: 6875971 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4668. Min Range: -5.4668
Max Act: 4.7168. Min Act: -0.1700
Data Index: 5777471 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19