Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3914 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0199. Min Range: -6.0199
Max Act: 6.0199. Min Act: -0.1700
Data Index: 8457783 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.9886. Min Act: -0.1700
Data Index: 4572421 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.9886. Min Act: -0.1700
Data Index: 7314265 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.9574. Min Act: -0.1700
Data Index: 5726325 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.8949. Min Act: -0.1700
Data Index: 1159572 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.8011. Min Act: -0.1700
Data Index: 2888005 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.8011. Min Act: -0.1700
Data Index: 571373 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.8011. Min Act: -0.1700
Data Index: 7673223 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.7386. Min Act: -0.1700
Data Index: 2428930 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.7386. Min Act: -0.1700
Data Index: 8434221 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.7386. Min Act: -0.1700
Data Index: 6139810 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.7074. Min Act: -0.1700
Data Index: 6706812 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.7074. Min Act: -0.1700
Data Index: 2428932 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.7074. Min Act: -0.1700
Data Index: 4071705 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.7074. Min Act: -0.1700
Data Index: 2561259 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.6761. Min Act: -0.1700
Data Index: 2570298 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.6761. Min Act: -0.1700
Data Index: 1473471 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.6761. Min Act: -0.1700
Data Index: 2428935 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.6761. Min Act: -0.1700
Data Index: 7365955 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0199. Min Range: -6.0199
Max Act: 5.6761. Min Act: -0.1700
Data Index: 3312116 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19