Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1241 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6216. Min Range: -9.6216
Max Act: 9.6216. Min Act: -0.1700
Data Index: 3679035 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6216. Min Range: -9.6216
Max Act: 9.6216. Min Act: -0.1700
Data Index: 4567054 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6216. Min Range: -9.6216
Max Act: 9.2466. Min Act: -0.1700
Data Index: 408153 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6216. Min Range: -9.6216
Max Act: 9.1841. Min Act: -0.1700
Data Index: 4878618 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6216. Min Range: -9.6216
Max Act: 9.1841. Min Act: -0.1700
Data Index: 8803358 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6216. Min Range: -9.6216
Max Act: 9.1216. Min Act: -0.1700
Data Index: 6699442 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6216. Min Range: -9.6216
Max Act: 9.1216. Min Act: -0.1700
Data Index: 189257 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6216. Min Range: -9.6216
Max Act: 9.1841. Min Act: -0.1700
Data Index: 5659824 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6216. Min Range: -9.6216
Max Act: 9.0591. Min Act: -0.1700
Data Index: 8460950 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6216. Min Range: -9.6216
Max Act: 8.9966. Min Act: -0.1700
Data Index: 1923463 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6216. Min Range: -9.6216
Max Act: 8.8716. Min Act: -0.1700
Data Index: 7312039 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6216. Min Range: -9.6216
Max Act: 8.9341. Min Act: -0.1700
Data Index: 1852131 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6216. Min Range: -9.6216
Max Act: 8.9341. Min Act: -0.1700
Data Index: 2061422 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6216. Min Range: -9.6216
Max Act: 8.9341. Min Act: -0.1700
Data Index: 7658765 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6216. Min Range: -9.6216
Max Act: 8.9966. Min Act: -0.1700
Data Index: 4629386 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6216. Min Range: -9.6216
Max Act: 8.9341. Min Act: -0.1700
Data Index: 8358489 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6216. Min Range: -9.6216
Max Act: 8.9341. Min Act: -0.1700
Data Index: 6319412 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6216. Min Range: -9.6216
Max Act: 8.9341. Min Act: -0.1700
Data Index: 3679034 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6216. Min Range: -9.6216
Max Act: 8.9341. Min Act: -0.1700
Data Index: 6691441 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6216. Min Range: -9.6216
Max Act: 8.9341. Min Act: -0.1700
Data Index: 4841363 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19