Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4958 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.9333. Min Act: -0.1700
Data Index: 5020192 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.9021. Min Act: -0.1700
Data Index: 8771282 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.8708. Min Act: -0.1700
Data Index: 1087993 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.8395. Min Act: -0.1700
Data Index: 4728743 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.8082. Min Act: -0.1700
Data Index: 2108812 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.8082. Min Act: -0.1700
Data Index: 6997610 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.8082. Min Act: -0.1700
Data Index: 340929 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.7770. Min Act: -0.1700
Data Index: 5934532 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.7457. Min Act: -0.1700
Data Index: 1031099 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.6988. Min Act: -0.1700
Data Index: 3910151 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.6675. Min Act: -0.1700
Data Index: 5970327 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.6988. Min Act: -0.1700
Data Index: 1031098 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.6988. Min Act: -0.1700
Data Index: 766922 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.6675. Min Act: -0.1700
Data Index: 4281152 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.6675. Min Act: -0.1700
Data Index: 2995492 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.6831. Min Act: -0.1700
Data Index: 458358 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.6518. Min Act: -0.1700
Data Index: 2158826 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.6518. Min Act: -0.1700
Data Index: 3420263 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.6362. Min Act: -0.1700
Data Index: 4807920 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9333. Min Range: -3.9333
Max Act: 3.6362. Min Act: -0.1700
Data Index: 2541204 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19