Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0690. Min Range: -6.0690
Max Act: 6.0690. Min Act: -0.1700
Data Index: 6665730 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.8502. Min Act: -0.1700
Data Index: 5055770 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.7252. Min Act: -0.1700
Data Index: 3953831 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.6315. Min Act: -0.1700
Data Index: 2780188 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.6315. Min Act: -0.1700
Data Index: 2396144 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.5377. Min Act: -0.1700
Data Index: 3828187 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.5377. Min Act: -0.1700
Data Index: 2534071 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.5377. Min Act: -0.1700
Data Index: 7439645 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.5377. Min Act: -0.1700
Data Index: 5730999 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.5065. Min Act: -0.1700
Data Index: 2839036 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.5065. Min Act: -0.1700
Data Index: 1094283 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.4440. Min Act: -0.1700
Data Index: 2461637 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.4440. Min Act: -0.1700
Data Index: 6313558 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.4440. Min Act: -0.1700
Data Index: 6415157 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.4440. Min Act: -0.1700
Data Index: 8169730 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.4440. Min Act: -0.1700
Data Index: 3157691 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.3815. Min Act: -0.1700
Data Index: 5985147 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.3815. Min Act: -0.1700
Data Index: 531445 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.3502. Min Act: -0.1700
Data Index: 3206012 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0690. Min Range: -6.0690
Max Act: 5.3502. Min Act: -0.1700
Data Index: 2762966 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19