Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.4743. Min Act: -0.1700
Data Index: 7707803 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.4743. Min Act: -0.1700
Data Index: 6937465 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.2868. Min Act: -0.1700
Data Index: 2187970 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.2556. Min Act: -0.1700
Data Index: 8678219 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.2243. Min Act: -0.1700
Data Index: 3396418 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.1618. Min Act: -0.1700
Data Index: 3605455 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.1306. Min Act: -0.1700
Data Index: 2140608 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.1306. Min Act: -0.1700
Data Index: 2534023 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.1306. Min Act: -0.1700
Data Index: 5826736 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.1618. Min Act: -0.1700
Data Index: 2823344 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.1306. Min Act: -0.1700
Data Index: 8731573 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.0993. Min Act: -0.1700
Data Index: 5002476 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.1306. Min Act: -0.1700
Data Index: 7684064 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.0681. Min Act: -0.1700
Data Index: 1480537 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.0681. Min Act: -0.1700
Data Index: 4004674 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.0681. Min Act: -0.1700
Data Index: 8531325 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.0368. Min Act: -0.1700
Data Index: 8819804 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.0368. Min Act: -0.1700
Data Index: 6403228 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.0056. Min Act: -0.1700
Data Index: 8777050 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4743. Min Range: -7.4743
Max Act: 7.0368. Min Act: -0.1700
Data Index: 3537979 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19