Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.9497. Min Act: -0.1700
Data Index: 3787138 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.8559. Min Act: -0.1700
Data Index: 7860153 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.8402. Min Act: -0.1700
Data Index: 5350736 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.7308. Min Act: -0.1700
Data Index: 3787136 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.7151. Min Act: -0.1700
Data Index: 3422243 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6682. Min Act: -0.1700
Data Index: 8394278 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6369. Min Act: -0.1700
Data Index: 8655309 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6056. Min Act: -0.1700
Data Index: 1221491 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.5743. Min Act: -0.1700
Data Index: 1191750 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.5586. Min Act: -0.1700
Data Index: 7485530 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.5430. Min Act: -0.1700
Data Index: 1904783 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.5430. Min Act: -0.1700
Data Index: 6943629 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.5273. Min Act: -0.1700
Data Index: 954526 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.5430. Min Act: -0.1700
Data Index: 663276 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.4960. Min Act: -0.1700
Data Index: 7647551 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.5117. Min Act: -0.1700
Data Index: 6161878 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.4803. Min Act: -0.1700
Data Index: 7140131 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.4803. Min Act: -0.1700
Data Index: 389745 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.4803. Min Act: -0.1700
Data Index: 8789671 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.4803. Min Act: -0.1700
Data Index: 2712393 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19