Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2863 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.6900. Min Act: -0.1700
Data Index: 1580288 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.6587. Min Act: -0.1700
Data Index: 939128 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.6275. Min Act: -0.1700
Data Index: 5751004 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.6275. Min Act: -0.1700
Data Index: 2167134 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.6275. Min Act: -0.1700
Data Index: 1280860 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.6275. Min Act: -0.1700
Data Index: 4684539 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.6587. Min Act: -0.1700
Data Index: 3476483 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5962. Min Act: -0.1700
Data Index: 1584511 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5962. Min Act: -0.1700
Data Index: 5318205 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5962. Min Act: -0.1700
Data Index: 6934614 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5962. Min Act: -0.1700
Data Index: 6400844 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5962. Min Act: -0.1700
Data Index: 7813703 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5962. Min Act: -0.1700
Data Index: 7580245 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5962. Min Act: -0.1700
Data Index: 7532351 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5337. Min Act: -0.1700
Data Index: 4797567 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5650. Min Act: -0.1700
Data Index: 6213588 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5650. Min Act: -0.1700
Data Index: 1586584 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5962. Min Act: -0.1700
Data Index: 4242080 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5650. Min Act: -0.1700
Data Index: 3112881 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6900. Min Range: -4.6900
Max Act: 4.5650. Min Act: -0.1700
Data Index: 5383949 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19