Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4944 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1549. Min Range: -5.1549
Max Act: 5.1549. Min Act: -0.1700
Data Index: 5461233 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1549. Min Range: -5.1549
Max Act: 5.1236. Min Act: -0.1700
Data Index: 8414937 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1549. Min Range: -5.1549
Max Act: 5.1236. Min Act: -0.1700
Data Index: 3661672 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1549. Min Range: -5.1549
Max Act: 5.0924. Min Act: -0.1700
Data Index: 3411223 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1549. Min Range: -5.1549
Max Act: 5.0924. Min Act: -0.1700
Data Index: 6420801 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1549. Min Range: -5.1549
Max Act: 4.9986. Min Act: -0.1700
Data Index: 1733343 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1549. Min Range: -5.1549
Max Act: 5.0299. Min Act: -0.1700
Data Index: 4827467 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1549. Min Range: -5.1549
Max Act: 5.0299. Min Act: -0.1700
Data Index: 5501720 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1549. Min Range: -5.1549
Max Act: 5.0299. Min Act: -0.1700
Data Index: 7200605 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1549. Min Range: -5.1549
Max Act: 4.9674. Min Act: -0.1700
Data Index: 2006829 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1549. Min Range: -5.1549
Max Act: 4.9361. Min Act: -0.1700
Data Index: 4177464 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1549. Min Range: -5.1549
Max Act: 4.9361. Min Act: -0.1700
Data Index: 4389085 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1549. Min Range: -5.1549
Max Act: 4.9049. Min Act: -0.1700
Data Index: 3470820 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1549. Min Range: -5.1549
Max Act: 4.8736. Min Act: -0.1700
Data Index: 8824490 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1549. Min Range: -5.1549
Max Act: 4.9049. Min Act: -0.1700
Data Index: 7718306 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1549. Min Range: -5.1549
Max Act: 4.9049. Min Act: -0.1700
Data Index: 4459083 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1549. Min Range: -5.1549
Max Act: 4.8736. Min Act: -0.1700
Data Index: 5703065 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1549. Min Range: -5.1549
Max Act: 4.8736. Min Act: -0.1700
Data Index: 4072770 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1549. Min Range: -5.1549
Max Act: 4.9049. Min Act: -0.1700
Data Index: 1695803 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1549. Min Range: -5.1549
Max Act: 4.8736. Min Act: -0.1700
Data Index: 758350 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19