Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.5015. Min Act: -0.1700
Data Index: 1240719 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.4702. Min Act: -0.1700
Data Index: 3389340 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.4077. Min Act: -0.1700
Data Index: 10636 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3765. Min Act: -0.1700
Data Index: 8444495 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3765. Min Act: -0.1700
Data Index: 8470608 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3765. Min Act: -0.1700
Data Index: 5575493 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3452. Min Act: -0.1700
Data Index: 3690490 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3452. Min Act: -0.1700
Data Index: 8378249 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3452. Min Act: -0.1700
Data Index: 4015921 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3452. Min Act: -0.1700
Data Index: 6567453 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3452. Min Act: -0.1700
Data Index: 3990885 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3452. Min Act: -0.1700
Data Index: 5155295 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3452. Min Act: -0.1700
Data Index: 2222406 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3452. Min Act: -0.1700
Data Index: 7812610 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3140. Min Act: -0.1700
Data Index: 4961770 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3140. Min Act: -0.1700
Data Index: 3002264 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3140. Min Act: -0.1700
Data Index: 5601555 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3140. Min Act: -0.1700
Data Index: 6064580 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3140. Min Act: -0.1700
Data Index: 1045986 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5015. Min Range: -4.5015
Max Act: 4.3140. Min Act: -0.1700
Data Index: 6568072 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19