Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.8019. Min Act: -0.1700
Data Index: 8339265 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.6769. Min Act: -0.1700
Data Index: 2315368 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.5206. Min Act: -0.1700
Data Index: 753398 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.4581. Min Act: -0.1700
Data Index: 6041650 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.4269. Min Act: -0.1700
Data Index: 8496053 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.4269. Min Act: -0.1700
Data Index: 6252814 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3956. Min Act: -0.1700
Data Index: 6432785 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3956. Min Act: -0.1700
Data Index: 4570256 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3331. Min Act: -0.1700
Data Index: 3409856 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3331. Min Act: -0.1700
Data Index: 6394220 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3019. Min Act: -0.1700
Data Index: 3181270 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3331. Min Act: -0.1700
Data Index: 3813555 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3019. Min Act: -0.1700
Data Index: 3540641 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3019. Min Act: -0.1700
Data Index: 6517935 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3019. Min Act: -0.1700
Data Index: 6589402 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3019. Min Act: -0.1700
Data Index: 6122848 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3019. Min Act: -0.1700
Data Index: 8008674 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3019. Min Act: -0.1700
Data Index: 7768670 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.2706. Min Act: -0.1700
Data Index: 7178627 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8019. Min Range: -4.8019
Max Act: 4.3019. Min Act: -0.1700
Data Index: 3530966 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19