Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1236 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.3602. Min Act: -0.1700
Data Index: 291295 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.3602. Min Act: -0.1699
Data Index: 7305806 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.2665. Min Act: -0.1699
Data Index: 2669780 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.2352. Min Act: -0.1699
Data Index: 6482626 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.2040. Min Act: -0.1700
Data Index: 8359972 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1727. Min Act: -0.1700
Data Index: 5926440 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.2040. Min Act: -0.1699
Data Index: 846162 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.2040. Min Act: -0.1700
Data Index: 8024140 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1727. Min Act: -0.1700
Data Index: 2086884 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1727. Min Act: -0.1700
Data Index: 4760868 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1727. Min Act: -0.1700
Data Index: 7432793 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1727. Min Act: -0.1700
Data Index: 5085046 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1414. Min Act: -0.1700
Data Index: 3600546 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1414. Min Act: -0.1698
Data Index: 6089924 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1102. Min Act: -0.1700
Data Index: 3224357 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1414. Min Act: -0.1700
Data Index: 1902700 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1414. Min Act: -0.1700
Data Index: 6611428 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1414. Min Act: -0.1698
Data Index: 7268301 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1414. Min Act: -0.1700
Data Index: 1792647 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3602. Min Range: -4.3602
Max Act: 4.1414. Min Act: -0.1700
Data Index: 4860187 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19