Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5835 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.8640. Min Act: -0.1700
Data Index: 225463 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.7078. Min Act: -0.1700
Data Index: 6713993 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.7078. Min Act: -0.1700
Data Index: 2158227 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.6140. Min Act: -0.1700
Data Index: 2638057 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.6140. Min Act: -0.1700
Data Index: 195448 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.5515. Min Act: -0.1700
Data Index: 323393 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.5515. Min Act: -0.1700
Data Index: 3365678 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.5515. Min Act: -0.1700
Data Index: 1988147 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.5203. Min Act: -0.1700
Data Index: 5631693 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.5203. Min Act: -0.1700
Data Index: 951418 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.5203. Min Act: -0.1700
Data Index: 693830 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.4890. Min Act: -0.1700
Data Index: 1476667 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.4890. Min Act: -0.1700
Data Index: 8007192 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.4265. Min Act: -0.1700
Data Index: 4965261 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.4578. Min Act: -0.1700
Data Index: 6022390 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.4265. Min Act: -0.1700
Data Index: 4849602 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.4265. Min Act: -0.1700
Data Index: 6286214 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.4578. Min Act: -0.1700
Data Index: 6956700 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.3953. Min Act: -0.1700
Data Index: 486598 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8640. Min Range: -5.8640
Max Act: 5.4265. Min Act: -0.1700
Data Index: 3086625 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19