Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.5701. Min Act: -0.1700
Data Index: 1779209 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.4764. Min Act: -0.1700
Data Index: 1788015 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.3826. Min Act: -0.1700
Data Index: 7198133 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.3201. Min Act: -0.1700
Data Index: 6028939 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.3514. Min Act: -0.1700
Data Index: 6961700 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.3201. Min Act: -0.1700
Data Index: 5709978 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.3201. Min Act: -0.1700
Data Index: 433347 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.3201. Min Act: -0.1700
Data Index: 4577853 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.3201. Min Act: -0.1700
Data Index: 24779 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.3201. Min Act: -0.1700
Data Index: 8514244 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.2889. Min Act: -0.1700
Data Index: 2904127 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.2889. Min Act: -0.1700
Data Index: 2287372 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.2889. Min Act: -0.1700
Data Index: 2738957 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.2889. Min Act: -0.1700
Data Index: 5431291 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.2889. Min Act: -0.1700
Data Index: 6976402 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.2264. Min Act: -0.1700
Data Index: 6351729 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.2576. Min Act: -0.1700
Data Index: 6788340 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.2264. Min Act: -0.1700
Data Index: 6068926 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.2889. Min Act: -0.1700
Data Index: 4692071 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5701. Min Range: -6.5701
Max Act: 6.2576. Min Act: -0.1700
Data Index: 534817 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19