Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5693 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1462. Min Range: -7.1462
Max Act: 7.1462. Min Act: -0.1700
Data Index: 4668011 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1462. Min Range: -7.1462
Max Act: 7.0212. Min Act: -0.1700
Data Index: 3632904 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.8649. Min Act: -0.1700
Data Index: 2417793 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.8337. Min Act: -0.1700
Data Index: 3897440 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.8024. Min Act: -0.1700
Data Index: 8212070 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.7712. Min Act: -0.1700
Data Index: 4898609 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.7399. Min Act: -0.1700
Data Index: 2516562 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.6149. Min Act: -0.1700
Data Index: 5543748 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.6462. Min Act: -0.1700
Data Index: 4422464 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.5837. Min Act: -0.1700
Data Index: 8329619 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.5212. Min Act: -0.1700
Data Index: 8623224 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.5212. Min Act: -0.1700
Data Index: 6866538 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.5212. Min Act: -0.1700
Data Index: 8541217 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.5212. Min Act: -0.1700
Data Index: 7744311 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.4899. Min Act: -0.1700
Data Index: 7703587 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.4899. Min Act: -0.1700
Data Index: 7015455 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.4899. Min Act: -0.1700
Data Index: 1107876 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.5212. Min Act: -0.1700
Data Index: 929145 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.4587. Min Act: -0.1700
Data Index: 7875788 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1462. Min Range: -7.1462
Max Act: 6.4587. Min Act: -0.1700
Data Index: 5732025 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19