Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 945 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0008. Min Range: -5.0008
Max Act: 5.0008. Min Act: -0.1700
Data Index: 2174200 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.9695. Min Act: -0.1700
Data Index: 4015813 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.9383. Min Act: -0.1700
Data Index: 1584598 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.9070. Min Act: -0.1700
Data Index: 5468464 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.8758. Min Act: -0.1700
Data Index: 8015501 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.8445. Min Act: -0.1700
Data Index: 3252723 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.8445. Min Act: -0.1700
Data Index: 860488 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.8445. Min Act: -0.1700
Data Index: 2623343 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.8445. Min Act: -0.1700
Data Index: 8576504 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.7820. Min Act: -0.1700
Data Index: 7316844 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.8133. Min Act: -0.1700
Data Index: 8168314 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.8133. Min Act: -0.1700
Data Index: 4551053 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.7820. Min Act: -0.1700
Data Index: 1100051 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.7508. Min Act: -0.1700
Data Index: 134297 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.7508. Min Act: -0.1700
Data Index: 816672 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.7508. Min Act: -0.1700
Data Index: 190606 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.7195. Min Act: -0.1700
Data Index: 436271 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.7195. Min Act: -0.1700
Data Index: 8168309 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.6883. Min Act: -0.1700
Data Index: 1654403 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.6570. Min Act: -0.1700
Data Index: 503209 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19