Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3151 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0952. Min Range: -6.0952
Max Act: 6.0952. Min Act: -0.1700
Data Index: 961802 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0952. Min Range: -6.0952
Max Act: 6.0327. Min Act: -0.1700
Data Index: 1169544 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0952. Min Range: -6.0952
Max Act: 6.0014. Min Act: -0.1700
Data Index: 1169547 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.9702. Min Act: -0.1700
Data Index: 1169541 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.9389. Min Act: -0.1700
Data Index: 1745850 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.9389. Min Act: -0.1700
Data Index: 5175443 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.9389. Min Act: -0.1700
Data Index: 4162737 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.9389. Min Act: -0.1700
Data Index: 7997724 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.9077. Min Act: -0.1700
Data Index: 5930811 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.8764. Min Act: -0.1700
Data Index: 1169543 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.8764. Min Act: -0.1700
Data Index: 7378368 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.8452. Min Act: -0.1700
Data Index: 3103054 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.8764. Min Act: -0.1700
Data Index: 357329 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.7827. Min Act: -0.1700
Data Index: 1169545 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.7514. Min Act: -0.1700
Data Index: 5101921 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.7514. Min Act: -0.1700
Data Index: 1169546 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.7514. Min Act: -0.1700
Data Index: 8504241 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.7514. Min Act: -0.1700
Data Index: 1169538 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.7202. Min Act: -0.1700
Data Index: 7762465 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0952. Min Range: -6.0952
Max Act: 5.7202. Min Act: -0.1700
Data Index: 3737035 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19