Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.9315. Min Act: -0.1700
Data Index: 7165867 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.9003. Min Act: -0.1700
Data Index: 5215396 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.8690. Min Act: -0.1700
Data Index: 613275 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.8690. Min Act: -0.1700
Data Index: 4737047 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.8377. Min Act: -0.1700
Data Index: 2930555 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.8065. Min Act: -0.1700
Data Index: 8363175 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.8065. Min Act: -0.1700
Data Index: 3389167 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.7752. Min Act: -0.1700
Data Index: 3846798 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.8065. Min Act: -0.1700
Data Index: 8206087 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.7596. Min Act: -0.1700
Data Index: 4796155 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.7596. Min Act: -0.1700
Data Index: 1920956 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.7283. Min Act: -0.1700
Data Index: 5079537 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.7126. Min Act: -0.1700
Data Index: 6945641 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.7283. Min Act: -0.1700
Data Index: 6492508 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.7283. Min Act: -0.1700
Data Index: 6954765 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.7126. Min Act: -0.1700
Data Index: 970579 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.7126. Min Act: -0.1700
Data Index: 280392 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.7283. Min Act: -0.1700
Data Index: 1701280 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.6970. Min Act: -0.1700
Data Index: 2424367 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9315. Min Range: -3.9315
Max Act: 3.6813. Min Act: -0.1700
Data Index: 3653271 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19