Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.5998. Min Act: -0.1700
Data Index: 1980658 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.4123. Min Act: -0.1700
Data Index: 3212232 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.4436. Min Act: -0.1700
Data Index: 8496361 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.4123. Min Act: -0.1700
Data Index: 5446742 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.3498. Min Act: -0.1700
Data Index: 3166067 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.3186. Min Act: -0.1700
Data Index: 8029233 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.2561. Min Act: -0.1700
Data Index: 2827827 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.2873. Min Act: -0.1700
Data Index: 6986208 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.2561. Min Act: -0.1700
Data Index: 4504764 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.2561. Min Act: -0.1700
Data Index: 40118 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.2561. Min Act: -0.1700
Data Index: 4981083 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.2561. Min Act: -0.1700
Data Index: 4687609 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.2561. Min Act: -0.1700
Data Index: 7492251 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.2248. Min Act: -0.1700
Data Index: 4896089 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.2248. Min Act: -0.1700
Data Index: 7724237 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.2248. Min Act: -0.1700
Data Index: 6222380 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.1935. Min Act: -0.1700
Data Index: 2141726 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.1935. Min Act: -0.1700
Data Index: 7483381 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.1935. Min Act: -0.1700
Data Index: 7080052 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5998. Min Range: -4.5998
Max Act: 4.1623. Min Act: -0.1700
Data Index: 914627 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19