Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 966 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.4568. Min Act: -0.1700
Data Index: 1372543 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.3006. Min Act: -0.1700
Data Index: 219877 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.2693. Min Act: -0.1700
Data Index: 580548 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.2068. Min Act: -0.1700
Data Index: 857519 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.1756. Min Act: -0.1700
Data Index: 3466197 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.1756. Min Act: -0.1700
Data Index: 5039276 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.1756. Min Act: -0.1700
Data Index: 8742956 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.1756. Min Act: -0.1700
Data Index: 5421825 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.1443. Min Act: -0.1700
Data Index: 984767 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.1131. Min Act: -0.1700
Data Index: 4549203 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.0818. Min Act: -0.1700
Data Index: 7900706 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.0506. Min Act: -0.1700
Data Index: 6153885 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.0506. Min Act: -0.1700
Data Index: 5021817 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.0193. Min Act: -0.1700
Data Index: 4287628 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.0193. Min Act: -0.1700
Data Index: 7817036 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.0193. Min Act: -0.1700
Data Index: 3485568 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.0193. Min Act: -0.1700
Data Index: 13474 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.0193. Min Act: -0.1700
Data Index: 4544870 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4568. Min Range: -5.4568
Max Act: 5.0193. Min Act: -0.1700
Data Index: 1412931 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4568. Min Range: -5.4568
Max Act: 4.9881. Min Act: -0.1700
Data Index: 7498507 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19