Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0360. Min Range: -8.0360
Max Act: 8.0360. Min Act: -0.1700
Data Index: 2767889 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.9735. Min Act: -0.1700
Data Index: 3523612 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.9110. Min Act: -0.1700
Data Index: 581307 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.8485. Min Act: -0.1700
Data Index: 884997 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.7860. Min Act: -0.1700
Data Index: 6543037 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.7547. Min Act: -0.1700
Data Index: 7130167 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.6297. Min Act: -0.1700
Data Index: 1223722 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5985. Min Act: -0.1700
Data Index: 1374030 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5985. Min Act: -0.1700
Data Index: 7979551 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5985. Min Act: -0.1700
Data Index: 5925101 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5672. Min Act: -0.1700
Data Index: 3183154 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5985. Min Act: -0.1700
Data Index: 2277751 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5672. Min Act: -0.1700
Data Index: 7969837 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5360. Min Act: -0.1700
Data Index: 6363786 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5360. Min Act: -0.1700
Data Index: 3047330 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5360. Min Act: -0.1700
Data Index: 3209618 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5672. Min Act: -0.1700
Data Index: 801960 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5360. Min Act: -0.1700
Data Index: 3540033 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5047. Min Act: -0.1700
Data Index: 6874141 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0360. Min Range: -8.0360
Max Act: 7.5047. Min Act: -0.1700
Data Index: 8679753 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19