Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 632 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.5671. Min Act: -0.1700
Data Index: 8697709 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.3796. Min Act: -0.1700
Data Index: 3963495 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.2546. Min Act: -0.1700
Data Index: 237011 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.1608. Min Act: -0.1700
Data Index: 2489909 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.1296. Min Act: -0.1700
Data Index: 1425764 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0983. Min Act: -0.1700
Data Index: 1326171 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0671. Min Act: -0.1700
Data Index: 901957 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0671. Min Act: -0.1700
Data Index: 2888768 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0671. Min Act: -0.1700
Data Index: 4006957 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0983. Min Act: -0.1700
Data Index: 709480 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0671. Min Act: -0.1700
Data Index: 8608574 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0358. Min Act: -0.1700
Data Index: 3833303 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0358. Min Act: -0.1700
Data Index: 1098137 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0358. Min Act: -0.1700
Data Index: 8104153 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0671. Min Act: -0.1700
Data Index: 3558412 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0358. Min Act: -0.1700
Data Index: 2725195 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0358. Min Act: -0.1700
Data Index: 2049500 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0046. Min Act: -0.1700
Data Index: 8083993 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0046. Min Act: -0.1700
Data Index: 7417433 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5671. Min Range: -6.5671
Max Act: 6.0046. Min Act: -0.1700
Data Index: 8095087 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19