Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3623 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.7385. Min Act: -0.1698
Data Index: 811901 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.6813. Min Act: -0.1700
Data Index: 8737801 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.6813. Min Act: -0.1700
Data Index: 4515520 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.6651. Min Act: -0.1698
Data Index: 466256 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.6570. Min Act: -0.1700
Data Index: 2519829 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.6410. Min Act: -0.1696
Data Index: 3766729 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.6250. Min Act: -0.1700
Data Index: 8261841 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.6250. Min Act: -0.1700
Data Index: 151284 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.6171. Min Act: -0.1700
Data Index: 4760108 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.6171. Min Act: -0.1700
Data Index: 6533045 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.6092. Min Act: -0.1700
Data Index: 6948173 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.6092. Min Act: -0.1700
Data Index: 1889919 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.5856. Min Act: -0.1700
Data Index: 5750929 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.5856. Min Act: -0.1700
Data Index: 3418667 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.5934. Min Act: -0.1700
Data Index: 7944248 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.5778. Min Act: -0.1686
Data Index: 1131510 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.5856. Min Act: -0.1700
Data Index: 8202731 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.5623. Min Act: -0.1694
Data Index: 1045741 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.5700. Min Act: -0.1700
Data Index: 1911395 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7385. Min Range: -0.7385
Max Act: 0.5700. Min Act: -0.1700
Data Index: 7291152 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19