Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.4743. Min Act: -0.1700
Data Index: 3351246 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.3493. Min Act: -0.1700
Data Index: 6099879 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.3180. Min Act: -0.1700
Data Index: 82402 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.2868. Min Act: -0.1700
Data Index: 1252448 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.1618. Min Act: -0.1700
Data Index: 6690332 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.1930. Min Act: -0.1700
Data Index: 2671329 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.1618. Min Act: -0.1700
Data Index: 1962661 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.1305. Min Act: -0.1700
Data Index: 6501942 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.1305. Min Act: -0.1700
Data Index: 6247895 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0993. Min Act: -0.1700
Data Index: 3772388 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0993. Min Act: -0.1700
Data Index: 2600210 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0993. Min Act: -0.1700
Data Index: 4876430 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0680. Min Act: -0.1700
Data Index: 7641895 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0680. Min Act: -0.1700
Data Index: 5174799 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0680. Min Act: -0.1700
Data Index: 1975078 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0368. Min Act: -0.1700
Data Index: 4501958 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0680. Min Act: -0.1700
Data Index: 6696855 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0368. Min Act: -0.1700
Data Index: 5419913 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0055. Min Act: -0.1700
Data Index: 1799090 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0368. Min Act: -0.1700
Data Index: 6583197 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19