Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3762 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.7304. Min Act: -0.1694
Data Index: 5122732 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.6784. Min Act: -0.1692
Data Index: 2160953 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.6958. Min Act: -0.1645
Data Index: 7947457 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.7131. Min Act: -0.1578
Data Index: 3539826 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.6262. Min Act: -0.1655
Data Index: 3561318 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.6262. Min Act: -0.1698
Data Index: 2711469 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.6436. Min Act: -0.1673
Data Index: 2552288 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.6262. Min Act: -0.1697
Data Index: 7288337 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.6262. Min Act: -0.1676
Data Index: 3369730 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.6088. Min Act: -0.1695
Data Index: 663998 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.6088. Min Act: -0.1700
Data Index: 7097636 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.6088. Min Act: -0.1699
Data Index: 4564511 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.6088. Min Act: -0.1688
Data Index: 6499274 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.6088. Min Act: -0.1699
Data Index: 5759585 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.5738. Min Act: -0.1699
Data Index: 3271727 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.5913. Min Act: -0.1698
Data Index: 6886178 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.5913. Min Act: -0.1690
Data Index: 2734832 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.5913. Min Act: -0.1698
Data Index: 1477859 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.5738. Min Act: -0.1700
Data Index: 2141789 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7304. Min Range: -1.7304
Max Act: 1.5738. Min Act: -0.1699
Data Index: 5432168 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19