Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5654 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7455. Min Range: -7.7455
Max Act: 7.7455. Min Act: -0.1700
Data Index: 5235014 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7455. Min Range: -7.7455
Max Act: 7.3393. Min Act: -0.1700
Data Index: 738238 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7455. Min Range: -7.7455
Max Act: 7.2768. Min Act: -0.1700
Data Index: 4273518 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7455. Min Range: -7.7455
Max Act: 7.2455. Min Act: -0.1700
Data Index: 5902906 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7455. Min Range: -7.7455
Max Act: 7.1518. Min Act: -0.1700
Data Index: 4427728 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7455. Min Range: -7.7455
Max Act: 7.1518. Min Act: -0.1700
Data Index: 1747489 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7455. Min Range: -7.7455
Max Act: 7.1205. Min Act: -0.1700
Data Index: 2200968 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7455. Min Range: -7.7455
Max Act: 7.0893. Min Act: -0.1700
Data Index: 7914220 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7455. Min Range: -7.7455
Max Act: 7.0893. Min Act: -0.1700
Data Index: 6573086 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7455. Min Range: -7.7455
Max Act: 7.0580. Min Act: -0.1700
Data Index: 6321109 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7455. Min Range: -7.7455
Max Act: 7.0893. Min Act: -0.1700
Data Index: 882757 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7455. Min Range: -7.7455
Max Act: 6.9955. Min Act: -0.1700
Data Index: 4992206 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7455. Min Range: -7.7455
Max Act: 6.9955. Min Act: -0.1700
Data Index: 286080 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7455. Min Range: -7.7455
Max Act: 6.9643. Min Act: -0.1700
Data Index: 3494687 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7455. Min Range: -7.7455
Max Act: 6.9643. Min Act: -0.1700
Data Index: 8106183 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7455. Min Range: -7.7455
Max Act: 6.9643. Min Act: -0.1700
Data Index: 4283499 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7455. Min Range: -7.7455
Max Act: 6.9643. Min Act: -0.1700
Data Index: 805107 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7455. Min Range: -7.7455
Max Act: 6.9330. Min Act: -0.1700
Data Index: 8400143 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7455. Min Range: -7.7455
Max Act: 6.9643. Min Act: -0.1700
Data Index: 5145273 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7455. Min Range: -7.7455
Max Act: 6.8705. Min Act: -0.1700
Data Index: 162002 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19