Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1416 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9374. Min Range: -10.9374
Max Act: 10.9374. Min Act: -0.1700
Data Index: 3060392 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9374. Min Range: -10.9374
Max Act: 10.7499. Min Act: -0.1700
Data Index: 768699 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9374. Min Range: -10.9374
Max Act: 10.2499. Min Act: -0.1700
Data Index: 4460160 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9374. Min Range: -10.9374
Max Act: 10.1249. Min Act: -0.1700
Data Index: 3824957 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9374. Min Range: -10.9374
Max Act: 10.1874. Min Act: -0.1700
Data Index: 8495173 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9374. Min Range: -10.9374
Max Act: 10.1249. Min Act: -0.1700
Data Index: 2297055 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9374. Min Range: -10.9374
Max Act: 10.0624. Min Act: -0.1700
Data Index: 7460256 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9374. Min Range: -10.9374
Max Act: 10.0624. Min Act: -0.1700
Data Index: 1570572 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9374. Min Range: -10.9374
Max Act: 10.0624. Min Act: -0.1700
Data Index: 6103365 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9374. Min Range: -10.9374
Max Act: 10.0624. Min Act: -0.1700
Data Index: 2635650 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9374. Min Range: -10.9374
Max Act: 9.9999. Min Act: -0.1700
Data Index: 2383859 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9374. Min Range: -10.9374
Max Act: 9.9999. Min Act: -0.1700
Data Index: 5177171 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9374. Min Range: -10.9374
Max Act: 9.9999. Min Act: -0.1700
Data Index: 7476215 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9374. Min Range: -10.9374
Max Act: 9.9374. Min Act: -0.1700
Data Index: 8172800 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9374. Min Range: -10.9374
Max Act: 9.9374. Min Act: -0.1700
Data Index: 3487726 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9374. Min Range: -10.9374
Max Act: 9.9374. Min Act: -0.1700
Data Index: 1101388 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9374. Min Range: -10.9374
Max Act: 9.9374. Min Act: -0.1700
Data Index: 3694373 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9374. Min Range: -10.9374
Max Act: 9.9374. Min Act: -0.1700
Data Index: 4253434 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9374. Min Range: -10.9374
Max Act: 9.9374. Min Act: -0.1700
Data Index: 3451093 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9374. Min Range: -10.9374
Max Act: 9.8749. Min Act: -0.1700
Data Index: 3288748 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19