Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.9524. Min Act: -0.1700
Data Index: 3098844 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.7649. Min Act: -0.1700
Data Index: 4014840 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.7024. Min Act: -0.1700
Data Index: 2970329 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.6399. Min Act: -0.1700
Data Index: 5240387 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.5774. Min Act: -0.1700
Data Index: 6761177 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.5774. Min Act: -0.1700
Data Index: 2336761 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.5774. Min Act: -0.1700
Data Index: 4931533 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.5149. Min Act: -0.1700
Data Index: 3929725 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.5149. Min Act: -0.1700
Data Index: 152759 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.5149. Min Act: -0.1700
Data Index: 7488241 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.5149. Min Act: -0.1700
Data Index: 2914524 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.4524. Min Act: -0.1700
Data Index: 5058447 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.3899. Min Act: -0.1700
Data Index: 781394 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.3274. Min Act: -0.1700
Data Index: 154223 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.3899. Min Act: -0.1700
Data Index: 4169529 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.3274. Min Act: -0.1700
Data Index: 3335801 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.3274. Min Act: -0.1700
Data Index: 4798045 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.3274. Min Act: -0.1700
Data Index: 4213193 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.2649. Min Act: -0.1700
Data Index: 1161646 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9524. Min Range: -8.9524
Max Act: 8.2649. Min Act: -0.1700
Data Index: 4717289 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19