Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2867 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.2599. Min Act: -0.1700
Data Index: 4373134 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.2599. Min Act: -0.1700
Data Index: 2967669 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.1662. Min Act: -0.1700
Data Index: 1178170 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.1349. Min Act: -0.1700
Data Index: 3047101 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.1349. Min Act: -0.1700
Data Index: 3935409 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.1349. Min Act: -0.1700
Data Index: 2351168 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.1037. Min Act: -0.1700
Data Index: 3628931 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.1349. Min Act: -0.1700
Data Index: 950922 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.0412. Min Act: -0.1700
Data Index: 1410619 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.0412. Min Act: -0.1700
Data Index: 4916240 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.0099. Min Act: -0.1700
Data Index: 1147174 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.0412. Min Act: -0.1700
Data Index: 8011584 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.0099. Min Act: -0.1700
Data Index: 5970272 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.0412. Min Act: -0.1700
Data Index: 2902032 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2599. Min Range: -5.2599
Max Act: 5.0099. Min Act: -0.1700
Data Index: 8651360 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2599. Min Range: -5.2599
Max Act: 4.9787. Min Act: -0.1700
Data Index: 3118324 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2599. Min Range: -5.2599
Max Act: 4.9787. Min Act: -0.1700
Data Index: 7379335 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2599. Min Range: -5.2599
Max Act: 4.9787. Min Act: -0.1700
Data Index: 4229313 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2599. Min Range: -5.2599
Max Act: 4.9787. Min Act: -0.1700
Data Index: 5925105 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2599. Min Range: -5.2599
Max Act: 4.9787. Min Act: -0.1700
Data Index: 5201615 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19