Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2392 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2531. Min Range: -6.2531
Max Act: 6.2531. Min Act: -0.1700
Data Index: 1502877 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2531. Min Range: -6.2531
Max Act: 6.2531. Min Act: -0.1700
Data Index: 1788765 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2531. Min Range: -6.2531
Max Act: 6.2531. Min Act: -0.1700
Data Index: 7348135 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2531. Min Range: -6.2531
Max Act: 6.2218. Min Act: -0.1700
Data Index: 2346657 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2531. Min Range: -6.2531
Max Act: 6.0968. Min Act: -0.1700
Data Index: 1313885 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2531. Min Range: -6.2531
Max Act: 6.0656. Min Act: -0.1700
Data Index: 849749 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2531. Min Range: -6.2531
Max Act: 6.0656. Min Act: -0.1700
Data Index: 568211 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2531. Min Range: -6.2531
Max Act: 6.0031. Min Act: -0.1700
Data Index: 1306118 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2531. Min Range: -6.2531
Max Act: 6.0031. Min Act: -0.1700
Data Index: 568212 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2531. Min Range: -6.2531
Max Act: 5.9406. Min Act: -0.1700
Data Index: 7040986 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2531. Min Range: -6.2531
Max Act: 5.9093. Min Act: -0.1700
Data Index: 2213723 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2531. Min Range: -6.2531
Max Act: 5.9093. Min Act: -0.1700
Data Index: 4726206 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2531. Min Range: -6.2531
Max Act: 5.8468. Min Act: -0.1700
Data Index: 2807175 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2531. Min Range: -6.2531
Max Act: 5.8468. Min Act: -0.1700
Data Index: 3103292 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2531. Min Range: -6.2531
Max Act: 5.8156. Min Act: -0.1700
Data Index: 6931316 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2531. Min Range: -6.2531
Max Act: 5.8468. Min Act: -0.1693
Data Index: 3651180 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2531. Min Range: -6.2531
Max Act: 5.7843. Min Act: -0.1700
Data Index: 8546658 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2531. Min Range: -6.2531
Max Act: 5.8156. Min Act: -0.1700
Data Index: 3084202 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2531. Min Range: -6.2531
Max Act: 5.7843. Min Act: -0.1700
Data Index: 5246692 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2531. Min Range: -6.2531
Max Act: 5.7843. Min Act: -0.1700
Data Index: 6589242 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19