Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3787 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.7140. Min Act: -0.1700
Data Index: 651770 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.5265. Min Act: -0.1700
Data Index: 1518214 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.3390. Min Act: -0.1700
Data Index: 3089291 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.2765. Min Act: -0.1700
Data Index: 7789056 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.2452. Min Act: -0.1700
Data Index: 2660804 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.1827. Min Act: -0.1700
Data Index: 7592256 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.1827. Min Act: -0.1700
Data Index: 1712384 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.1827. Min Act: -0.1700
Data Index: 7001703 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.1515. Min Act: -0.1700
Data Index: 1389258 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.1515. Min Act: -0.1700
Data Index: 1209448 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.1515. Min Act: -0.1700
Data Index: 6400793 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.1202. Min Act: -0.1700
Data Index: 2799369 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.0890. Min Act: -0.1700
Data Index: 3792304 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.1202. Min Act: -0.1700
Data Index: 3872386 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.0577. Min Act: -0.1700
Data Index: 4553947 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.0577. Min Act: -0.1700
Data Index: 3538723 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.0577. Min Act: -0.1700
Data Index: 7772297 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.0577. Min Act: -0.1700
Data Index: 2308225 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7140. Min Range: -5.7140
Max Act: 4.9952. Min Act: -0.1700
Data Index: 7319750 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7140. Min Range: -5.7140
Max Act: 5.0265. Min Act: -0.1700
Data Index: 4926668 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19