Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 139 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0448. Min Range: -6.0448
Max Act: 6.0448. Min Act: -0.1700
Data Index: 7894482 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0448. Min Range: -6.0448
Max Act: 6.0448. Min Act: -0.1700
Data Index: 2573138 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.9198. Min Act: -0.1700
Data Index: 5421982 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.9510. Min Act: -0.1700
Data Index: 2962418 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.9198. Min Act: -0.1700
Data Index: 4104342 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.8573. Min Act: -0.1700
Data Index: 1915847 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.8885. Min Act: -0.1700
Data Index: 1571858 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.8573. Min Act: -0.1700
Data Index: 239593 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.7948. Min Act: -0.1700
Data Index: 4045919 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.7948. Min Act: -0.1700
Data Index: 6963726 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.7635. Min Act: -0.1700
Data Index: 7744976 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.7635. Min Act: -0.1700
Data Index: 2132953 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.7635. Min Act: -0.1700
Data Index: 4156448 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.7323. Min Act: -0.1700
Data Index: 2353417 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.7323. Min Act: -0.1700
Data Index: 8322737 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.7323. Min Act: -0.1700
Data Index: 5168910 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.7323. Min Act: -0.1700
Data Index: 1518551 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.7323. Min Act: -0.1700
Data Index: 1418945 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.7010. Min Act: -0.1700
Data Index: 1402981 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0448. Min Range: -6.0448
Max Act: 5.7010. Min Act: -0.1700
Data Index: 8402095 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19