Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2971. Min Range: -3.2971
Max Act: 3.2971. Min Act: -0.1700
Data Index: 1076516 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2971. Min Range: -3.2971
Max Act: 3.0611. Min Act: -0.1700
Data Index: 7473105 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2971. Min Range: -3.2971
Max Act: 3.0611. Min Act: -0.1700
Data Index: 3558442 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2971. Min Range: -3.2971
Max Act: 3.0295. Min Act: -0.1700
Data Index: 508341 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2971. Min Range: -3.2971
Max Act: 3.0138. Min Act: -0.1700
Data Index: 424940 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2971. Min Range: -3.2971
Max Act: 3.0138. Min Act: -0.1700
Data Index: 3725931 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.9980. Min Act: -0.1700
Data Index: 2171617 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2971. Min Range: -3.2971
Max Act: 3.0138. Min Act: -0.1700
Data Index: 7142801 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.9821. Min Act: -0.1700
Data Index: 498227 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.9821. Min Act: -0.1700
Data Index: 4030858 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.9663. Min Act: -0.1700
Data Index: 7473155 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.9980. Min Act: -0.1700
Data Index: 6363674 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.9980. Min Act: -0.1700
Data Index: 3922351 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.9663. Min Act: -0.1700
Data Index: 5525015 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.9347. Min Act: -0.1700
Data Index: 4561392 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.9188. Min Act: -0.1700
Data Index: 3205076 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.8871. Min Act: -0.1700
Data Index: 3922348 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.9030. Min Act: -0.1700
Data Index: 5126839 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.9030. Min Act: -0.1700
Data Index: 6014357 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2971. Min Range: -3.2971
Max Act: 2.9030. Min Act: -0.1700
Data Index: 7469794 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19