Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2084 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.3140. Min Act: -0.1700
Data Index: 4173593 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.2515. Min Act: -0.1700
Data Index: 5962852 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.2515. Min Act: -0.1700
Data Index: 5877643 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.2202. Min Act: -0.1700
Data Index: 2012301 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.1577. Min Act: -0.1700
Data Index: 4983795 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.1265. Min Act: -0.1700
Data Index: 5167750 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.1265. Min Act: -0.1700
Data Index: 3644013 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.0640. Min Act: -0.1700
Data Index: 4426790 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.0640. Min Act: -0.1700
Data Index: 455431 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.0327. Min Act: -0.1700
Data Index: 4774788 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.0327. Min Act: -0.1700
Data Index: 4851951 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.0327. Min Act: -0.1700
Data Index: 1963783 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.0015. Min Act: -0.1700
Data Index: 1422437 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3140. Min Range: -5.3140
Max Act: 5.0015. Min Act: -0.1700
Data Index: 101357 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3140. Min Range: -5.3140
Max Act: 4.9390. Min Act: -0.1700
Data Index: 8193156 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3140. Min Range: -5.3140
Max Act: 4.9390. Min Act: -0.1700
Data Index: 4958717 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3140. Min Range: -5.3140
Max Act: 4.9390. Min Act: -0.1700
Data Index: 62729 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3140. Min Range: -5.3140
Max Act: 4.9077. Min Act: -0.1700
Data Index: 6919 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3140. Min Range: -5.3140
Max Act: 4.9077. Min Act: -0.1700
Data Index: 174753 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3140. Min Range: -5.3140
Max Act: 4.9077. Min Act: -0.1700
Data Index: 5839503 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19