Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3913 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0663. Min Range: -7.0663
Max Act: 7.0663. Min Act: -0.1700
Data Index: 7739703 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.9725. Min Act: -0.1700
Data Index: 2559148 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.9725. Min Act: -0.1700
Data Index: 4981019 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.8475. Min Act: -0.1700
Data Index: 2668057 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.8475. Min Act: -0.1700
Data Index: 243516 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.8475. Min Act: -0.1700
Data Index: 7620954 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.8788. Min Act: -0.1700
Data Index: 3791745 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.8163. Min Act: -0.1700
Data Index: 8177943 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.8163. Min Act: -0.1700
Data Index: 4786260 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.8163. Min Act: -0.1700
Data Index: 311321 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.8475. Min Act: -0.1700
Data Index: 1206293 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.6600. Min Act: -0.1700
Data Index: 8789665 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.6600. Min Act: -0.1700
Data Index: 6044824 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.6288. Min Act: -0.1700
Data Index: 7842188 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.5663. Min Act: -0.1700
Data Index: 4849776 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.6288. Min Act: -0.1700
Data Index: 3610964 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.5975. Min Act: -0.1700
Data Index: 4027427 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.5975. Min Act: -0.1700
Data Index: 6169450 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.5975. Min Act: -0.1700
Data Index: 1188579 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0663. Min Range: -7.0663
Max Act: 6.5975. Min Act: -0.1700
Data Index: 2147414 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19