Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.6459. Min Act: -0.1700
Data Index: 3884418 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.6146. Min Act: -0.1700
Data Index: 2945130 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.6146. Min Act: -0.1700
Data Index: 2761940 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.5834. Min Act: -0.1700
Data Index: 976309 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.5834. Min Act: -0.1700
Data Index: 7032079 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4896. Min Act: -0.1700
Data Index: 6753235 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4896. Min Act: -0.1700
Data Index: 882810 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4271. Min Act: -0.1700
Data Index: 7081990 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.3959. Min Act: -0.1700
Data Index: 954868 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.3959. Min Act: -0.1700
Data Index: 3082235 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4271. Min Act: -0.1700
Data Index: 4757998 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.4271. Min Act: -0.1700
Data Index: 804461 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.3959. Min Act: -0.1700
Data Index: 7245748 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.3646. Min Act: -0.1700
Data Index: 3011315 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.3959. Min Act: -0.1700
Data Index: 8551404 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.3646. Min Act: -0.1700
Data Index: 1393728 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.3646. Min Act: -0.1700
Data Index: 1042105 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.3334. Min Act: -0.1700
Data Index: 1033305 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.3646. Min Act: -0.1700
Data Index: 7758874 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6459. Min Range: -4.6459
Max Act: 4.3646. Min Act: -0.1700
Data Index: 2730017 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19