Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 430 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0018. Min Range: -2.0018
Max Act: 2.0018. Min Act: -0.1700
Data Index: 6797140 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.9340. Min Act: -0.1700
Data Index: 6682783 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8743. Min Act: -0.1700
Data Index: 1002254 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8743. Min Act: -0.1700
Data Index: 248791 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8743. Min Act: -0.1700
Data Index: 6996671 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8828. Min Act: -0.1700
Data Index: 147341 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8657. Min Act: -0.1700
Data Index: 8099098 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8657. Min Act: -0.1700
Data Index: 4174273 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8486. Min Act: -0.1698
Data Index: 2252179 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8743. Min Act: -0.1700
Data Index: 8657195 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8486. Min Act: -0.1700
Data Index: 7873453 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8486. Min Act: -0.1700
Data Index: 4558749 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8486. Min Act: -0.1700
Data Index: 7781091 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8486. Min Act: -0.1700
Data Index: 5374464 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8572. Min Act: -0.1700
Data Index: 3786720 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8401. Min Act: -0.1700
Data Index: 6861469 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8401. Min Act: -0.1700
Data Index: 7278040 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8486. Min Act: -0.1700
Data Index: 4151088 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8315. Min Act: -0.1700
Data Index: 8260184 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0018. Min Range: -2.0018
Max Act: 1.8229. Min Act: -0.1700
Data Index: 5615375 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19