Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1663 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.9878. Min Act: -0.1700
Data Index: 5960195 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8927. Min Act: -0.1699
Data Index: 4774130 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8610. Min Act: -0.1700
Data Index: 5212946 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.8610. Min Act: -0.1700
Data Index: 8332837 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.7815. Min Act: -0.1676
Data Index: 2736637 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.7974. Min Act: -0.1700
Data Index: 5917864 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.7496. Min Act: -0.1700
Data Index: 8135719 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.7655. Min Act: -0.1700
Data Index: 1422673 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.7496. Min Act: -0.1700
Data Index: 6631903 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.7176. Min Act: -0.1700
Data Index: 5032888 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.7016. Min Act: -0.1700
Data Index: 2914528 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.7016. Min Act: -0.1700
Data Index: 8060110 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.6856. Min Act: -0.1700
Data Index: 1422672 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.7016. Min Act: -0.1700
Data Index: 2042633 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.6856. Min Act: -0.1700
Data Index: 6625720 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.6856. Min Act: -0.1700
Data Index: 4285498 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.6856. Min Act: -0.1700
Data Index: 1208040 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.6856. Min Act: -0.1700
Data Index: 7734020 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.7016. Min Act: -0.1700
Data Index: 1210507 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9878. Min Range: -2.9878
Max Act: 2.6535. Min Act: -0.1700
Data Index: 2736633 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19