Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2484 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0336. Min Range: -6.0336
Max Act: 6.0336. Min Act: -0.1700
Data Index: 3591522 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.6898. Min Act: -0.1700
Data Index: 7273496 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.6586. Min Act: -0.1700
Data Index: 6015188 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.6586. Min Act: -0.1700
Data Index: 5572826 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.6273. Min Act: -0.1700
Data Index: 3193923 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.5648. Min Act: -0.1700
Data Index: 3243213 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.5648. Min Act: -0.1700
Data Index: 1148709 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.4711. Min Act: -0.1700
Data Index: 8759055 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.4086. Min Act: -0.1700
Data Index: 654602 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.4086. Min Act: -0.1700
Data Index: 3041345 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.3773. Min Act: -0.1700
Data Index: 4384408 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.3773. Min Act: -0.1700
Data Index: 5431850 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.3461. Min Act: -0.1700
Data Index: 3911896 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.3461. Min Act: -0.1700
Data Index: 939543 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.3148. Min Act: -0.1700
Data Index: 2171298 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.3148. Min Act: -0.1700
Data Index: 8036990 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.3148. Min Act: -0.1700
Data Index: 2047798 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.2836. Min Act: -0.1700
Data Index: 2311776 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.2836. Min Act: -0.1700
Data Index: 8142964 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0336. Min Range: -6.0336
Max Act: 5.2836. Min Act: -0.1700
Data Index: 5750718 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19