Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5285 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8997. Min Range: -8.8997
Max Act: 8.8997. Min Act: -0.1700
Data Index: 1306400 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8997. Min Range: -8.8997
Max Act: 8.3997. Min Act: -0.1700
Data Index: 5066425 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8997. Min Range: -8.8997
Max Act: 8.2747. Min Act: -0.1700
Data Index: 2174268 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8997. Min Range: -8.8997
Max Act: 8.1497. Min Act: -0.1700
Data Index: 5082720 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8997. Min Range: -8.8997
Max Act: 8.1497. Min Act: -0.1700
Data Index: 6692778 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8997. Min Range: -8.8997
Max Act: 8.1497. Min Act: -0.1700
Data Index: 2844884 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8997. Min Range: -8.8997
Max Act: 8.0872. Min Act: -0.1700
Data Index: 6101298 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8997. Min Range: -8.8997
Max Act: 8.0872. Min Act: -0.1700
Data Index: 710724 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8997. Min Range: -8.8997
Max Act: 8.0872. Min Act: -0.1700
Data Index: 1522946 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8997. Min Range: -8.8997
Max Act: 8.0872. Min Act: -0.1700
Data Index: 6325261 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8997. Min Range: -8.8997
Max Act: 7.9622. Min Act: -0.1700
Data Index: 2176542 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8997. Min Range: -8.8997
Max Act: 8.0247. Min Act: -0.1700
Data Index: 2380737 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8997. Min Range: -8.8997
Max Act: 7.8997. Min Act: -0.1700
Data Index: 5766614 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8997. Min Range: -8.8997
Max Act: 7.9622. Min Act: -0.1700
Data Index: 3339084 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8997. Min Range: -8.8997
Max Act: 7.9622. Min Act: -0.1700
Data Index: 7415782 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8997. Min Range: -8.8997
Max Act: 7.9622. Min Act: -0.1700
Data Index: 5556701 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8997. Min Range: -8.8997
Max Act: 7.9622. Min Act: -0.1700
Data Index: 3769484 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8997. Min Range: -8.8997
Max Act: 7.9622. Min Act: -0.1700
Data Index: 83947 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8997. Min Range: -8.8997
Max Act: 7.9622. Min Act: -0.1700
Data Index: 520241 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8997. Min Range: -8.8997
Max Act: 7.9622. Min Act: -0.1700
Data Index: 6171884 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19