Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5122 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0652. Min Range: -3.0652
Max Act: 3.0495. Min Act: -0.1700
Data Index: 7105547 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0652. Min Range: -3.0652
Max Act: 3.0652. Min Act: -0.1700
Data Index: 6247343 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0652. Min Range: -3.0652
Max Act: 3.0495. Min Act: -0.1700
Data Index: 823678 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0652. Min Range: -3.0652
Max Act: 3.0021. Min Act: -0.1700
Data Index: 6627051 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0652. Min Range: -3.0652
Max Act: 3.0179. Min Act: -0.1700
Data Index: 2125338 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0652. Min Range: -3.0652
Max Act: 3.0021. Min Act: -0.1700
Data Index: 5651176 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0652. Min Range: -3.0652
Max Act: 3.0021. Min Act: -0.1700
Data Index: 3948346 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9546. Min Act: -0.1700
Data Index: 1688307 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9705. Min Act: -0.1700
Data Index: 4835220 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9546. Min Act: -0.1700
Data Index: 1082920 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9705. Min Act: -0.1700
Data Index: 8089593 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9546. Min Act: -0.1700
Data Index: 1761004 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9546. Min Act: -0.1700
Data Index: 4296501 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9546. Min Act: -0.1700
Data Index: 6719064 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9546. Min Act: -0.1700
Data Index: 7935156 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9388. Min Act: -0.1700
Data Index: 260677 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9230. Min Act: -0.1700
Data Index: 7164480 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9230. Min Act: -0.1700
Data Index: 5856815 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9230. Min Act: -0.1700
Data Index: 3788682 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0652. Min Range: -3.0652
Max Act: 2.9230. Min Act: -0.1700
Data Index: 6441634 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19