Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3972. Min Range: -9.3972
Max Act: 9.3972. Min Act: -0.1700
Data Index: 1980747 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3972. Min Range: -9.3972
Max Act: 9.2722. Min Act: -0.1700
Data Index: 7594485 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3972. Min Range: -9.3972
Max Act: 9.1472. Min Act: -0.1700
Data Index: 1792968 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3972. Min Range: -9.3972
Max Act: 9.0847. Min Act: -0.1700
Data Index: 6947064 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.9597. Min Act: -0.1700
Data Index: 5312954 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.9597. Min Act: -0.1700
Data Index: 5277743 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.9597. Min Act: -0.1700
Data Index: 2991685 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.8972. Min Act: -0.1700
Data Index: 8280298 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.8347. Min Act: -0.1700
Data Index: 545950 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.8347. Min Act: -0.1700
Data Index: 8216730 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.8347. Min Act: -0.1700
Data Index: 1126629 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.8347. Min Act: -0.1700
Data Index: 2247726 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.8347. Min Act: -0.1700
Data Index: 3808674 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.8347. Min Act: -0.1700
Data Index: 4210668 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.8347. Min Act: -0.1700
Data Index: 3343385 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.7722. Min Act: -0.1700
Data Index: 299221 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.7097. Min Act: -0.1700
Data Index: 6592618 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.7097. Min Act: -0.1700
Data Index: 5920749 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.6472. Min Act: -0.1700
Data Index: 1380003 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3972. Min Range: -9.3972
Max Act: 8.6472. Min Act: -0.1700
Data Index: 6615493 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19