Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1144 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.2235. Min Act: -0.1700
Data Index: 3610598 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.2235. Min Act: -0.1700
Data Index: 1603197 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.2235. Min Act: -0.1700
Data Index: 5850426 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.1610. Min Act: -0.1700
Data Index: 6411061 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.1610. Min Act: -0.1700
Data Index: 6719892 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.1610. Min Act: -0.1700
Data Index: 7437805 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.1298. Min Act: -0.1700
Data Index: 2719698 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0985. Min Act: -0.1700
Data Index: 933126 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0985. Min Act: -0.1700
Data Index: 1503211 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0985. Min Act: -0.1700
Data Index: 6591363 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0985. Min Act: -0.1700
Data Index: 95690 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0360. Min Act: -0.1700
Data Index: 1634492 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0673. Min Act: -0.1700
Data Index: 3367248 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0673. Min Act: -0.1700
Data Index: 755054 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0673. Min Act: -0.1700
Data Index: 7508939 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0673. Min Act: -0.1700
Data Index: 7042240 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0673. Min Act: -0.1700
Data Index: 4600861 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0673. Min Act: -0.1700
Data Index: 4308298 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0673. Min Act: -0.1700
Data Index: 3796924 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.0360. Min Act: -0.1700
Data Index: 3524690 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19