Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1666 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.2556. Min Act: -0.1700
Data Index: 5212725 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.1931. Min Act: -0.1700
Data Index: 8718490 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.1619. Min Act: -0.1700
Data Index: 1872209 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.1931. Min Act: -0.1700
Data Index: 2527474 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.1306. Min Act: -0.1700
Data Index: 2029794 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0994. Min Act: -0.1700
Data Index: 6540402 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0994. Min Act: -0.1700
Data Index: 3452347 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0681. Min Act: -0.1700
Data Index: 136935 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0681. Min Act: -0.1700
Data Index: 6564372 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0681. Min Act: -0.1700
Data Index: 1081510 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0681. Min Act: -0.1700
Data Index: 8607125 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0681. Min Act: -0.1700
Data Index: 8062755 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0369. Min Act: -0.1700
Data Index: 6436061 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0056. Min Act: -0.1700
Data Index: 5872299 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0056. Min Act: -0.1700
Data Index: 6433990 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0056. Min Act: -0.1700
Data Index: 2241396 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0056. Min Act: -0.1700
Data Index: 3055124 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0056. Min Act: -0.1700
Data Index: 6894436 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2556. Min Range: -5.2556
Max Act: 5.0056. Min Act: -0.1700
Data Index: 4791554 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2556. Min Range: -5.2556
Max Act: 4.9744. Min Act: -0.1700
Data Index: 241675 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19