Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4185 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.6142. Min Act: -0.1700
Data Index: 5561097 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.4267. Min Act: -0.1700
Data Index: 5765004 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.4267. Min Act: -0.1700
Data Index: 3085548 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2392. Min Act: -0.1700
Data Index: 5205204 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2392. Min Act: -0.1700
Data Index: 2092028 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.2080. Min Act: -0.1700
Data Index: 1981142 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.1455. Min Act: -0.1700
Data Index: 1184249 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.1767. Min Act: -0.1700
Data Index: 5128589 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.1767. Min Act: -0.1700
Data Index: 1166894 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.1455. Min Act: -0.1700
Data Index: 1184250 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.1455. Min Act: -0.1700
Data Index: 1954963 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.1455. Min Act: -0.1700
Data Index: 4390033 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.1142. Min Act: -0.1700
Data Index: 392711 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.0830. Min Act: -0.1700
Data Index: 3009119 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.0830. Min Act: -0.1700
Data Index: 2501283 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.0830. Min Act: -0.1700
Data Index: 6435869 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.0830. Min Act: -0.1700
Data Index: 3255185 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.0830. Min Act: -0.1700
Data Index: 3640863 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.0830. Min Act: -0.1700
Data Index: 2422118 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6142. Min Range: -5.6142
Max Act: 5.0517. Min Act: -0.1700
Data Index: 4314462 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19