Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1825 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.6686. Min Range: -10.6686
Max Act: 10.6686. Min Act: -0.1700
Data Index: 3453064 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6686. Min Range: -10.6686
Max Act: 10.1061. Min Act: -0.1700
Data Index: 3754020 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6686. Min Range: -10.6686
Max Act: 10.1061. Min Act: -0.1700
Data Index: 3796921 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.9186. Min Act: -0.1700
Data Index: 7248929 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.9811. Min Act: -0.1700
Data Index: 4814090 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.9186. Min Act: -0.1700
Data Index: 5209578 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.8561. Min Act: -0.1700
Data Index: 6744827 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.8561. Min Act: -0.1700
Data Index: 3409149 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.8561. Min Act: -0.1700
Data Index: 8625857 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.8561. Min Act: -0.1700
Data Index: 5320659 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.7936. Min Act: -0.1700
Data Index: 4113360 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.7936. Min Act: -0.1699
Data Index: 2728336 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.7936. Min Act: -0.1700
Data Index: 1209115 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.7311. Min Act: -0.1700
Data Index: 5113392 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.7311. Min Act: -0.1700
Data Index: 4158945 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.7311. Min Act: -0.1700
Data Index: 3140474 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.7936. Min Act: -0.1700
Data Index: 3606899 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.6686. Min Act: -0.1700
Data Index: 6284678 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.6686. Min Act: -0.1700
Data Index: 3687153 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6686. Min Range: -10.6686
Max Act: 9.6686. Min Act: -0.1700
Data Index: 224187 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19