Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1588 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.2697. Min Act: -0.1700
Data Index: 8315980 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.2697. Min Act: -0.1700
Data Index: 1375342 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.2385. Min Act: -0.1700
Data Index: 1064625 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.2385. Min Act: -0.1700
Data Index: 2194149 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.1760. Min Act: -0.1700
Data Index: 5343027 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.1447. Min Act: -0.1700
Data Index: 3616016 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.1760. Min Act: -0.1700
Data Index: 1436886 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.1135. Min Act: -0.1700
Data Index: 2388441 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.0822. Min Act: -0.1700
Data Index: 8315981 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.1135. Min Act: -0.1700
Data Index: 58846 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.0510. Min Act: -0.1700
Data Index: 980789 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.0510. Min Act: -0.1700
Data Index: 4179983 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.0510. Min Act: -0.1700
Data Index: 8412509 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.0510. Min Act: -0.1700
Data Index: 2649399 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.0510. Min Act: -0.1700
Data Index: 308823 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.0510. Min Act: -0.1700
Data Index: 8411611 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.0510. Min Act: -0.1700
Data Index: 58851 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.0510. Min Act: -0.1700
Data Index: 1375341 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.0197. Min Act: -0.1700
Data Index: 1393841 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2697. Min Range: -5.2697
Max Act: 5.0197. Min Act: -0.1700
Data Index: 8511612 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19