Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.5176. Min Act: -0.1700
Data Index: 1937986 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.3926. Min Act: -0.1700
Data Index: 1780149 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.3614. Min Act: -0.1700
Data Index: 7140401 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.3301. Min Act: -0.1700
Data Index: 8129549 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.3301. Min Act: -0.1700
Data Index: 5296038 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.2676. Min Act: -0.1700
Data Index: 3430015 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.2364. Min Act: -0.1700
Data Index: 4765897 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.2364. Min Act: -0.1700
Data Index: 3923460 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.1739. Min Act: -0.1700
Data Index: 3841711 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.1426. Min Act: -0.1700
Data Index: 5824913 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.1114. Min Act: -0.1700
Data Index: 7713302 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.0489. Min Act: -0.1700
Data Index: 7415380 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.0801. Min Act: -0.1700
Data Index: 1761428 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.0801. Min Act: -0.1700
Data Index: 429187 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.0801. Min Act: -0.1700
Data Index: 324999 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.0489. Min Act: -0.1700
Data Index: 1784628 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.0176. Min Act: -0.1700
Data Index: 6090232 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.0176. Min Act: -0.1700
Data Index: 668847 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.0176. Min Act: -0.1700
Data Index: 3145354 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5176. Min Range: -7.5176
Max Act: 7.0176. Min Act: -0.1700
Data Index: 5470503 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19