Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1055 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.7670. Min Act: -0.1700
Data Index: 3634624 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.7045. Min Act: -0.1700
Data Index: 545285 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.5795. Min Act: -0.1700
Data Index: 150418 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.5170. Min Act: -0.1700
Data Index: 6669926 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.5170. Min Act: -0.1700
Data Index: 7680542 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.5170. Min Act: -0.1700
Data Index: 3470164 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.4545. Min Act: -0.1700
Data Index: 3673564 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.4545. Min Act: -0.1700
Data Index: 8574983 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.3920. Min Act: -0.1700
Data Index: 7023467 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.3920. Min Act: -0.1700
Data Index: 3962123 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.3920. Min Act: -0.1700
Data Index: 1145928 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.3920. Min Act: -0.1700
Data Index: 6059346 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.3920. Min Act: -0.1700
Data Index: 2756091 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.3295. Min Act: -0.1700
Data Index: 4645089 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.3295. Min Act: -0.1700
Data Index: 8760684 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.3295. Min Act: -0.1700
Data Index: 2178392 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.3295. Min Act: -0.1700
Data Index: 2289910 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.3295. Min Act: -0.1700
Data Index: 1415571 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.2670. Min Act: -0.1700
Data Index: 282447 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7670. Min Range: -8.7670
Max Act: 8.2670. Min Act: -0.1700
Data Index: 342681 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19