Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0335. Min Range: -8.0335
Max Act: 8.0335. Min Act: -0.1700
Data Index: 2727592 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.9710. Min Act: -0.1700
Data Index: 7016641 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.9710. Min Act: -0.1700
Data Index: 5970579 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.9710. Min Act: -0.1700
Data Index: 100704 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.9085. Min Act: -0.1700
Data Index: 5368435 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.7835. Min Act: -0.1700
Data Index: 2417968 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.7835. Min Act: -0.1700
Data Index: 862393 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.7210. Min Act: -0.1700
Data Index: 3183478 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.7210. Min Act: -0.1700
Data Index: 6204836 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.7210. Min Act: -0.1700
Data Index: 6865149 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.7210. Min Act: -0.1700
Data Index: 8589569 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.6585. Min Act: -0.1700
Data Index: 1996248 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.6585. Min Act: -0.1700
Data Index: 5588298 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.7210. Min Act: -0.1700
Data Index: 5076640 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.6585. Min Act: -0.1700
Data Index: 3038533 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.6585. Min Act: -0.1700
Data Index: 7437663 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.6585. Min Act: -0.1700
Data Index: 7133447 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.5960. Min Act: -0.1700
Data Index: 6950265 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.5960. Min Act: -0.1700
Data Index: 2828125 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0335. Min Range: -8.0335
Max Act: 7.5960. Min Act: -0.1700
Data Index: 4501098 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19