Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.7241. Min Act: -0.1700
Data Index: 7486416 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.3491. Min Act: -0.1700
Data Index: 7049726 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.1616. Min Act: -0.1700
Data Index: 1722096 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.0991. Min Act: -0.1700
Data Index: 4314652 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.0366. Min Act: -0.1700
Data Index: 7263813 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.0054. Min Act: -0.1700
Data Index: 7881954 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.9741. Min Act: -0.1700
Data Index: 6908963 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7241. Min Range: -6.7241
Max Act: 6.0054. Min Act: -0.1700
Data Index: 6651108 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.9741. Min Act: -0.1700
Data Index: 6369851 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.9741. Min Act: -0.1700
Data Index: 6048994 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.9741. Min Act: -0.1700
Data Index: 5330877 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.9429. Min Act: -0.1700
Data Index: 4790937 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.9429. Min Act: -0.1700
Data Index: 7636356 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.9116. Min Act: -0.1700
Data Index: 4361102 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.9116. Min Act: -0.1700
Data Index: 3283287 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.8804. Min Act: -0.1700
Data Index: 6803827 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.8491. Min Act: -0.1700
Data Index: 3173189 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.8804. Min Act: -0.1700
Data Index: 6818186 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.8804. Min Act: -0.1700
Data Index: 7080009 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7241. Min Range: -6.7241
Max Act: 5.8491. Min Act: -0.1700
Data Index: 5489492 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19