Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.8618. Min Act: -0.1700
Data Index: 1886941 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.8305. Min Act: -0.1700
Data Index: 6438842 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7680. Min Act: -0.1700
Data Index: 3251082 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7368. Min Act: -0.1700
Data Index: 1523121 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7368. Min Act: -0.1700
Data Index: 740507 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7368. Min Act: -0.1700
Data Index: 3627335 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7055. Min Act: -0.1700
Data Index: 2449075 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7055. Min Act: -0.1700
Data Index: 4997897 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7055. Min Act: -0.1700
Data Index: 2420548 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6743. Min Act: -0.1700
Data Index: 1524232 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6430. Min Act: -0.1700
Data Index: 7115555 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5805. Min Act: -0.1700
Data Index: 8511186 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.6118. Min Act: -0.1700
Data Index: 2125198 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5493. Min Act: -0.1700
Data Index: 7275704 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4868. Min Act: -0.1700
Data Index: 1915861 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4868. Min Act: -0.1700
Data Index: 1523120 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4243. Min Act: -0.1700
Data Index: 8791157 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4555. Min Act: -0.1700
Data Index: 7995989 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4868. Min Act: -0.1700
Data Index: 1467155 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4243. Min Act: -0.1700
Data Index: 6649821 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19