Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1573 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1594. Min Range: -4.1594
Max Act: 4.1594. Min Act: -0.1700
Data Index: 2204065 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1594. Min Range: -4.1594
Max Act: 4.0656. Min Act: -0.1700
Data Index: 8304665 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1594. Min Range: -4.1594
Max Act: 4.0031. Min Act: -0.1700
Data Index: 1624149 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1594. Min Range: -4.1594
Max Act: 4.0031. Min Act: -0.1700
Data Index: 6954113 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.9718. Min Act: -0.1700
Data Index: 7901026 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.9406. Min Act: -0.1700
Data Index: 223167 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.9406. Min Act: -0.1700
Data Index: 4606084 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.9406. Min Act: -0.1700
Data Index: 8112459 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.9406. Min Act: -0.1700
Data Index: 956419 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.9093. Min Act: -0.1700
Data Index: 394551 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.9093. Min Act: -0.1700
Data Index: 6721001 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.9093. Min Act: -0.1700
Data Index: 7223705 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.8311. Min Act: -0.1700
Data Index: 4723546 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.8468. Min Act: -0.1700
Data Index: 8188189 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.8468. Min Act: -0.1700
Data Index: 540845 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.8155. Min Act: -0.1700
Data Index: 8654947 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.8155. Min Act: -0.1700
Data Index: 3830278 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.8311. Min Act: -0.1700
Data Index: 7916624 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.8155. Min Act: -0.1700
Data Index: 2185931 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1594. Min Range: -4.1594
Max Act: 3.8311. Min Act: -0.1700
Data Index: 2202881 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19