Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.3908. Min Act: -0.1700
Data Index: 4701858 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.3283. Min Act: -0.1700
Data Index: 5704069 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.2658. Min Act: -0.1700
Data Index: 220784 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.2345. Min Act: -0.1700
Data Index: 4993578 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.1720. Min Act: -0.1700
Data Index: 3346177 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.1408. Min Act: -0.1700
Data Index: 643512 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.1408. Min Act: -0.1700
Data Index: 1123431 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.1408. Min Act: -0.1700
Data Index: 4090274 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.1408. Min Act: -0.1698
Data Index: 4808343 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.1095. Min Act: -0.1700
Data Index: 2445586 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.1095. Min Act: -0.1700
Data Index: 5838652 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.0783. Min Act: -0.1700
Data Index: 4448696 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.0783. Min Act: -0.1700
Data Index: 7600841 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.0783. Min Act: -0.1700
Data Index: 1362340 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.1095. Min Act: -0.1700
Data Index: 2510123 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.0470. Min Act: -0.1700
Data Index: 5076053 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.0158. Min Act: -0.1700
Data Index: 5606933 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.0470. Min Act: -0.1700
Data Index: 4795 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3908. Min Range: -6.3908
Max Act: 6.0470. Min Act: -0.1700
Data Index: 4074590 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3908. Min Range: -6.3908
Max Act: 5.9845. Min Act: -0.1700
Data Index: 6564978 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19