Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1870 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.6515. Min Act: -0.1700
Data Index: 3903783 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.6515. Min Act: -0.1700
Data Index: 4051823 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.6358. Min Act: -0.1700
Data Index: 8464742 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5889. Min Act: -0.1700
Data Index: 607927 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.6202. Min Act: -0.1700
Data Index: 8052923 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5889. Min Act: -0.1700
Data Index: 2078858 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5419. Min Act: -0.1700
Data Index: 4600249 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5263. Min Act: -0.1700
Data Index: 1118109 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5106. Min Act: -0.1700
Data Index: 5212590 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5106. Min Act: -0.1700
Data Index: 3765301 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5106. Min Act: -0.1700
Data Index: 1272868 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5106. Min Act: -0.1700
Data Index: 7267661 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5106. Min Act: -0.1700
Data Index: 4015452 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5106. Min Act: -0.1700
Data Index: 5571793 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5106. Min Act: -0.1700
Data Index: 209885 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4949. Min Act: -0.1700
Data Index: 8593553 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5106. Min Act: -0.1700
Data Index: 977210 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4793. Min Act: -0.1700
Data Index: 935202 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4636. Min Act: -0.1700
Data Index: 7699843 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4636. Min Act: -0.1700
Data Index: 607929 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19