Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0774. Min Range: -2.0774
Max Act: 2.0774. Min Act: -0.1700
Data Index: 651544 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0774. Min Range: -2.0774
Max Act: 2.0270. Min Act: -0.1700
Data Index: 845069 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0774. Min Range: -2.0774
Max Act: 2.0270. Min Act: -0.1700
Data Index: 1821107 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0774. Min Range: -2.0774
Max Act: 2.0270. Min Act: -0.1700
Data Index: 5501358 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9932. Min Act: -0.1700
Data Index: 8177977 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9763. Min Act: -0.1700
Data Index: 2410546 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9763. Min Act: -0.1699
Data Index: 5501360 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9593. Min Act: -0.1700
Data Index: 1793143 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9423. Min Act: -0.1700
Data Index: 5807461 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9423. Min Act: -0.1698
Data Index: 7918178 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9423. Min Act: -0.1700
Data Index: 4159952 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9253. Min Act: -0.1700
Data Index: 5623917 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9253. Min Act: -0.1700
Data Index: 3212260 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9083. Min Act: -0.1700
Data Index: 7603535 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9253. Min Act: -0.1700
Data Index: 7589477 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9253. Min Act: -0.1700
Data Index: 6314340 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9423. Min Act: -0.1700
Data Index: 6181472 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9253. Min Act: -0.1700
Data Index: 5066615 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9253. Min Act: -0.1700
Data Index: 3766177 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0774. Min Range: -2.0774
Max Act: 1.9083. Min Act: -0.1700
Data Index: 5547466 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19