Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3215 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.8557. Min Act: -0.1700
Data Index: 5016036 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.8088. Min Act: -0.1700
Data Index: 423102 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.7775. Min Act: -0.1700
Data Index: 3230752 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.7619. Min Act: -0.1700
Data Index: 2101527 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.7619. Min Act: -0.1700
Data Index: 6032155 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.7150. Min Act: -0.1700
Data Index: 2319836 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.7150. Min Act: -0.1700
Data Index: 4989379 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.7150. Min Act: -0.1700
Data Index: 2695280 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.7150. Min Act: -0.1700
Data Index: 6355462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.6993. Min Act: -0.1700
Data Index: 6892375 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.6681. Min Act: -0.1700
Data Index: 6932306 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.6681. Min Act: -0.1700
Data Index: 2695276 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.6681. Min Act: -0.1700
Data Index: 6188873 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.6524. Min Act: -0.1700
Data Index: 2619904 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.6368. Min Act: -0.1700
Data Index: 6135076 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.6211. Min Act: -0.1700
Data Index: 3672751 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.6211. Min Act: -0.1700
Data Index: 4456723 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.6211. Min Act: -0.1700
Data Index: 8690187 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.5898. Min Act: -0.1700
Data Index: 859326 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8557. Min Range: -3.8557
Max Act: 3.5742. Min Act: -0.1700
Data Index: 1948935 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19