Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.3774. Min Act: -0.1700
Data Index: 5309522 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.3462. Min Act: -0.1700
Data Index: 6277178 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1899. Min Act: -0.1700
Data Index: 8740047 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.2212. Min Act: -0.1700
Data Index: 3302635 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.2212. Min Act: -0.1700
Data Index: 1512071 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1899. Min Act: -0.1700
Data Index: 2952150 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1899. Min Act: -0.1700
Data Index: 2435934 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1899. Min Act: -0.1700
Data Index: 3844009 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1587. Min Act: -0.1700
Data Index: 690409 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1587. Min Act: -0.1700
Data Index: 6026017 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1587. Min Act: -0.1700
Data Index: 1914486 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1587. Min Act: -0.1700
Data Index: 5186948 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1587. Min Act: -0.1700
Data Index: 7758168 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1274. Min Act: -0.1700
Data Index: 2435933 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1587. Min Act: -0.1700
Data Index: 8386254 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1274. Min Act: -0.1700
Data Index: 6857874 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1274. Min Act: -0.1700
Data Index: 2316553 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.1274. Min Act: -0.1700
Data Index: 5586958 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.0962. Min Act: -0.1700
Data Index: 2401682 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3774. Min Range: -5.3774
Max Act: 5.0649. Min Act: -0.1700
Data Index: 2271621 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19