Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.8591. Min Act: -0.1700
Data Index: 5057078 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.7966. Min Act: -0.1700
Data Index: 331685 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.6404. Min Act: -0.1700
Data Index: 5186452 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.5466. Min Act: -0.1700
Data Index: 5366062 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.5779. Min Act: -0.1700
Data Index: 4097803 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.4841. Min Act: -0.1700
Data Index: 1158586 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.4529. Min Act: -0.1700
Data Index: 414212 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.4529. Min Act: -0.1700
Data Index: 7924741 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.4529. Min Act: -0.1700
Data Index: 3232443 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.3904. Min Act: -0.1700
Data Index: 2370792 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.3591. Min Act: -0.1700
Data Index: 5959662 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.3904. Min Act: -0.1700
Data Index: 3791362 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.3279. Min Act: -0.1700
Data Index: 6333583 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2966. Min Act: -0.1700
Data Index: 1720513 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2966. Min Act: -0.1700
Data Index: 2638984 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2966. Min Act: -0.1700
Data Index: 8504867 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2654. Min Act: -0.1700
Data Index: 7385639 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2341. Min Act: -0.1700
Data Index: 1248480 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2341. Min Act: -0.1700
Data Index: 2818423 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2341. Min Act: -0.1700
Data Index: 2429421 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19