Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5282 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5627. Min Range: -6.5627
Max Act: 6.5627. Min Act: -0.1700
Data Index: 7181066 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.7502. Min Act: -0.1700
Data Index: 4138812 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.6877. Min Act: -0.1700
Data Index: 423248 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.7189. Min Act: -0.1700
Data Index: 441335 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.6564. Min Act: -0.1700
Data Index: 7714299 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.6877. Min Act: -0.1700
Data Index: 1110991 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.6564. Min Act: -0.1700
Data Index: 5914529 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.6564. Min Act: -0.1700
Data Index: 1391531 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.6252. Min Act: -0.1700
Data Index: 8762252 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.6564. Min Act: -0.1700
Data Index: 7772043 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.5939. Min Act: -0.1700
Data Index: 4999691 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.5627. Min Act: -0.1700
Data Index: 345656 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.5627. Min Act: -0.1700
Data Index: 1516623 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.5314. Min Act: -0.1700
Data Index: 5739232 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.5314. Min Act: -0.1700
Data Index: 4890880 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.5314. Min Act: -0.1700
Data Index: 2260496 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.5314. Min Act: -0.1700
Data Index: 1437082 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.5314. Min Act: -0.1700
Data Index: 2027632 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.5002. Min Act: -0.1700
Data Index: 2257720 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5627. Min Range: -6.5627
Max Act: 5.4689. Min Act: -0.1700
Data Index: 7227190 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19