Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2698 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.7029. Min Act: -0.1700
Data Index: 5640469 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6403. Min Act: -0.1700
Data Index: 8137494 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6403. Min Act: -0.1700
Data Index: 5050365 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6403. Min Act: -0.1700
Data Index: 4814200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6403. Min Act: -0.1700
Data Index: 102149 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6403. Min Act: -0.1700
Data Index: 580151 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6403. Min Act: -0.1700
Data Index: 713581 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6403. Min Act: -0.1700
Data Index: 8329235 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6403. Min Act: -0.1700
Data Index: 5898456 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6403. Min Act: -0.1700
Data Index: 2456321 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6403. Min Act: -0.1700
Data Index: 7781745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6090. Min Act: -0.1700
Data Index: 4301267 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6090. Min Act: -0.1700
Data Index: 4476223 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6090. Min Act: -0.1700
Data Index: 2589818 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6090. Min Act: -0.1700
Data Index: 3767059 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6090. Min Act: -0.1700
Data Index: 2846662 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6090. Min Act: -0.1700
Data Index: 6256663 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6090. Min Act: -0.1700
Data Index: 2307490 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6090. Min Act: -0.1700
Data Index: 583177 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7029. Min Range: -3.7029
Max Act: 3.6090. Min Act: -0.1700
Data Index: 7477802 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19