Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3964 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.8387. Min Act: -0.1700
Data Index: 4130005 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.8387. Min Act: -0.1700
Data Index: 4384451 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.8387. Min Act: -0.1700
Data Index: 3077110 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.8075. Min Act: -0.1700
Data Index: 6093852 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.8075. Min Act: -0.1700
Data Index: 7719042 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.7762. Min Act: -0.1700
Data Index: 1633173 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.7762. Min Act: -0.1700
Data Index: 8287932 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.7762. Min Act: -0.1700
Data Index: 2235695 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.7450. Min Act: -0.1700
Data Index: 7194385 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.7450. Min Act: -0.1700
Data Index: 8027305 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.7450. Min Act: -0.1700
Data Index: 6897479 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.7137. Min Act: -0.1700
Data Index: 8222942 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.7137. Min Act: -0.1700
Data Index: 5818022 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.7137. Min Act: -0.1700
Data Index: 5963636 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.6512. Min Act: -0.1700
Data Index: 784269 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.6512. Min Act: -0.1700
Data Index: 1874569 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.6825. Min Act: -0.1700
Data Index: 8812078 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.5887. Min Act: -0.1700
Data Index: 2190351 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.6512. Min Act: -0.1700
Data Index: 2150002 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8387. Min Range: -5.8387
Max Act: 5.5887. Min Act: -0.1700
Data Index: 3455838 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19