Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6008 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6996. Min Act: -0.1700
Data Index: 2249332 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6683. Min Act: -0.1700
Data Index: 3973777 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6370. Min Act: -0.1700
Data Index: 6458797 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6213. Min Act: -0.1700
Data Index: 3095 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5900. Min Act: -0.1700
Data Index: 2539453 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.6057. Min Act: -0.1700
Data Index: 5772550 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5744. Min Act: -0.1700
Data Index: 4938079 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5744. Min Act: -0.1700
Data Index: 8410390 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5587. Min Act: -0.1700
Data Index: 7884647 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5431. Min Act: -0.1700
Data Index: 2053033 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5587. Min Act: -0.1700
Data Index: 3977844 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5587. Min Act: -0.1700
Data Index: 5127604 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5431. Min Act: -0.1700
Data Index: 4906772 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5431. Min Act: -0.1700
Data Index: 2957677 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5587. Min Act: -0.1700
Data Index: 4737729 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5431. Min Act: -0.1700
Data Index: 1343249 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5117. Min Act: -0.1700
Data Index: 675541 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5117. Min Act: -0.1700
Data Index: 8142319 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.5274. Min Act: -0.1700
Data Index: 8113366 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6996. Min Range: -3.6996
Max Act: 3.4961. Min Act: -0.1700
Data Index: 693059 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19