Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3784 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1433. Min Range: -5.1433
Max Act: 5.1433. Min Act: -0.1700
Data Index: 1906792 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1433. Min Range: -5.1433
Max Act: 5.1433. Min Act: -0.1700
Data Index: 292481 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1433. Min Range: -5.1433
Max Act: 5.0183. Min Act: -0.1700
Data Index: 5691357 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.9870. Min Act: -0.1700
Data Index: 1844443 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.9557. Min Act: -0.1700
Data Index: 604924 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.9557. Min Act: -0.1700
Data Index: 4656925 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.9245. Min Act: -0.1700
Data Index: 1381250 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.8932. Min Act: -0.1700
Data Index: 8036793 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.8932. Min Act: -0.1700
Data Index: 5767030 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.8932. Min Act: -0.1700
Data Index: 6408728 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.8620. Min Act: -0.1700
Data Index: 3206036 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.8620. Min Act: -0.1700
Data Index: 175944 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.8620. Min Act: -0.1700
Data Index: 7384271 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.8307. Min Act: -0.1700
Data Index: 8036794 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.8307. Min Act: -0.1700
Data Index: 6020229 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.7995. Min Act: -0.1700
Data Index: 8606994 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.7995. Min Act: -0.1700
Data Index: 2952697 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.7995. Min Act: -0.1700
Data Index: 3684487 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.7682. Min Act: -0.1700
Data Index: 1287868 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1433. Min Range: -5.1433
Max Act: 4.7682. Min Act: -0.1700
Data Index: 4895361 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19