Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3987 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4854. Min Act: -0.1700
Data Index: 7046953 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4854. Min Act: -0.1700
Data Index: 3985305 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4229. Min Act: -0.1700
Data Index: 1840880 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4542. Min Act: -0.1700
Data Index: 5338392 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4542. Min Act: -0.1700
Data Index: 7737072 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4542. Min Act: -0.1700
Data Index: 8417608 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4229. Min Act: -0.1700
Data Index: 4374446 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4229. Min Act: -0.1700
Data Index: 5595577 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4229. Min Act: -0.1700
Data Index: 1813493 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.3917. Min Act: -0.1700
Data Index: 962621 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4229. Min Act: -0.1700
Data Index: 5104263 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4229. Min Act: -0.1700
Data Index: 7847335 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.3917. Min Act: -0.1700
Data Index: 3403428 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.3917. Min Act: -0.1700
Data Index: 2163478 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4229. Min Act: -0.1700
Data Index: 4497185 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.4229. Min Act: -0.1700
Data Index: 7687019 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.3917. Min Act: -0.1700
Data Index: 5769533 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.3917. Min Act: -0.1700
Data Index: 4093768 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.3917. Min Act: -0.1700
Data Index: 1592429 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4854. Min Range: -4.4854
Max Act: 4.3917. Min Act: -0.1700
Data Index: 404026 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19