Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 871 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.6814. Min Act: -0.1700
Data Index: 1180971 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.5562. Min Act: -0.1700
Data Index: 4523806 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.5562. Min Act: -0.1700
Data Index: 4013695 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.5562. Min Act: -0.1700
Data Index: 3933769 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.5562. Min Act: -0.1700
Data Index: 3694390 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4935. Min Act: -0.1700
Data Index: 5414387 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4935. Min Act: -0.1700
Data Index: 6474099 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4935. Min Act: -0.1700
Data Index: 7830614 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4935. Min Act: -0.1700
Data Index: 3584426 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4622. Min Act: -0.1700
Data Index: 757676 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4622. Min Act: -0.1700
Data Index: 8120666 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4622. Min Act: -0.1700
Data Index: 5942138 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4622. Min Act: -0.1700
Data Index: 3341615 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4622. Min Act: -0.1700
Data Index: 7170727 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4622. Min Act: -0.1700
Data Index: 4465173 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4622. Min Act: -0.1700
Data Index: 2331532 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4622. Min Act: -0.1700
Data Index: 7928486 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4622. Min Act: -0.1700
Data Index: 2949925 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4308. Min Act: -0.1700
Data Index: 1277055 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6814. Min Range: -3.6814
Max Act: 3.4308. Min Act: -0.1700
Data Index: 4437811 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19