Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5083 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.6897. Min Act: -0.1700
Data Index: 5225935 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.6584. Min Act: -0.1700
Data Index: 1459634 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.5647. Min Act: -0.1700
Data Index: 2232304 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.5022. Min Act: -0.1700
Data Index: 2492377 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.4709. Min Act: -0.1700
Data Index: 3187334 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.4709. Min Act: -0.1700
Data Index: 2793103 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.4709. Min Act: -0.1700
Data Index: 8268189 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.4709. Min Act: -0.1700
Data Index: 3292491 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.4084. Min Act: -0.1700
Data Index: 5682691 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.4084. Min Act: -0.1700
Data Index: 7507897 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.3772. Min Act: -0.1700
Data Index: 3612823 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.3772. Min Act: -0.1700
Data Index: 1021240 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.3459. Min Act: -0.1700
Data Index: 1572678 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.3459. Min Act: -0.1700
Data Index: 654774 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.3459. Min Act: -0.1700
Data Index: 128904 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.3147. Min Act: -0.1700
Data Index: 8740607 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.3147. Min Act: -0.1700
Data Index: 1458453 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.2834. Min Act: -0.1700
Data Index: 2759196 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.3147. Min Act: -0.1700
Data Index: 2238402 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6897. Min Range: -6.6897
Max Act: 6.2834. Min Act: -0.1700
Data Index: 6861544 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19