Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3150 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5751. Min Act: -0.1700
Data Index: 115163 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5439. Min Act: -0.1700
Data Index: 1129970 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5439. Min Act: -0.1700
Data Index: 1339916 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5439. Min Act: -0.1700
Data Index: 6633750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5439. Min Act: -0.1700
Data Index: 5511471 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5126. Min Act: -0.1700
Data Index: 4695559 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5126. Min Act: -0.1700
Data Index: 8775829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5126. Min Act: -0.1699
Data Index: 7556413 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5126. Min Act: -0.1700
Data Index: 5583556 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5126. Min Act: -0.1700
Data Index: 3972996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.5439. Min Act: -0.1700
Data Index: 214602 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.4814. Min Act: -0.1700
Data Index: 1046343 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.4814. Min Act: -0.1700
Data Index: 7515564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.4814. Min Act: -0.1700
Data Index: 5763059 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.4814. Min Act: -0.1700
Data Index: 4385772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.4814. Min Act: -0.1700
Data Index: 3478523 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.4814. Min Act: -0.1700
Data Index: 5325062 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.4189. Min Act: -0.1700
Data Index: 1913704 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.4501. Min Act: -0.1700
Data Index: 1198705 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5751. Min Range: -5.5751
Max Act: 5.4814. Min Act: -0.1700
Data Index: 2751311 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19