Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4476 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.7278. Min Act: -0.1700
Data Index: 4614472 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.5716. Min Act: -0.1700
Data Index: 8419917 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.5403. Min Act: -0.1700
Data Index: 5445027 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.5403. Min Act: -0.1700
Data Index: 1163387 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.5091. Min Act: -0.1700
Data Index: 7659808 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.4153. Min Act: -0.1700
Data Index: 6668108 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.3841. Min Act: -0.1700
Data Index: 3177510 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.3528. Min Act: -0.1700
Data Index: 3887916 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.3528. Min Act: -0.1700
Data Index: 535116 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.3528. Min Act: -0.1700
Data Index: 4903798 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.3216. Min Act: -0.1700
Data Index: 1705148 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.3216. Min Act: -0.1700
Data Index: 5722240 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.3216. Min Act: -0.1700
Data Index: 5496781 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.3216. Min Act: -0.1700
Data Index: 3217869 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.3216. Min Act: -0.1700
Data Index: 1714296 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.2903. Min Act: -0.1700
Data Index: 2973226 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.2903. Min Act: -0.1700
Data Index: 6567272 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.2591. Min Act: -0.1700
Data Index: 8505957 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.2903. Min Act: -0.1700
Data Index: 8512252 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7278. Min Range: -5.7278
Max Act: 5.2591. Min Act: -0.1700
Data Index: 939037 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19