Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2258 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1408. Min Range: -7.1408
Max Act: 7.1408. Min Act: -0.1700
Data Index: 7296345 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1408. Min Range: -7.1408
Max Act: 7.0783. Min Act: -0.1700
Data Index: 6020542 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.9845. Min Act: -0.1700
Data Index: 3008182 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.7970. Min Act: -0.1700
Data Index: 1067430 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.7970. Min Act: -0.1700
Data Index: 4526340 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.7658. Min Act: -0.1700
Data Index: 2009082 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.7658. Min Act: -0.1700
Data Index: 6195595 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.7345. Min Act: -0.1700
Data Index: 6741748 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.7658. Min Act: -0.1700
Data Index: 7138840 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.7345. Min Act: -0.1700
Data Index: 8068423 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.7033. Min Act: -0.1700
Data Index: 8599412 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.7033. Min Act: -0.1700
Data Index: 5036599 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.7345. Min Act: -0.1700
Data Index: 6773649 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.7033. Min Act: -0.1700
Data Index: 7181484 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.6408. Min Act: -0.1700
Data Index: 944658 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.6095. Min Act: -0.1700
Data Index: 6768432 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.6095. Min Act: -0.1700
Data Index: 6664065 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.5783. Min Act: -0.1700
Data Index: 3167193 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.5470. Min Act: -0.1700
Data Index: 5100473 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1408. Min Range: -7.1408
Max Act: 6.5783. Min Act: -0.1700
Data Index: 5805110 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19