Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2765. Min Range: -4.2765
Max Act: 4.2765. Min Act: -0.1700
Data Index: 5036638 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2765. Min Range: -4.2765
Max Act: 4.2140. Min Act: -0.1700
Data Index: 5076712 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2765. Min Range: -4.2765
Max Act: 4.1515. Min Act: -0.1700
Data Index: 4526217 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2765. Min Range: -4.2765
Max Act: 4.1203. Min Act: -0.1700
Data Index: 4690414 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2765. Min Range: -4.2765
Max Act: 4.1203. Min Act: -0.1700
Data Index: 3815124 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2765. Min Range: -4.2765
Max Act: 4.0265. Min Act: -0.1700
Data Index: 2364993 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2765. Min Range: -4.2765
Max Act: 4.0265. Min Act: -0.1700
Data Index: 5105719 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2765. Min Range: -4.2765
Max Act: 4.0265. Min Act: -0.1700
Data Index: 863600 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2765. Min Range: -4.2765
Max Act: 3.9952. Min Act: -0.1700
Data Index: 7139732 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2765. Min Range: -4.2765
Max Act: 3.9952. Min Act: -0.1700
Data Index: 4167414 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2765. Min Range: -4.2765
Max Act: 3.9952. Min Act: -0.1700
Data Index: 7042292 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2765. Min Range: -4.2765
Max Act: 3.9952. Min Act: -0.1700
Data Index: 58940 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2765. Min Range: -4.2765
Max Act: 3.9952. Min Act: -0.1700
Data Index: 7576412 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2765. Min Range: -4.2765
Max Act: 3.9952. Min Act: -0.1700
Data Index: 6401410 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2765. Min Range: -4.2765
Max Act: 3.9952. Min Act: -0.1700
Data Index: 5888368 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2765. Min Range: -4.2765
Max Act: 3.9640. Min Act: -0.1700
Data Index: 7419341 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2765. Min Range: -4.2765
Max Act: 3.9640. Min Act: -0.1700
Data Index: 744204 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2765. Min Range: -4.2765
Max Act: 3.9640. Min Act: -0.1700
Data Index: 7080243 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2765. Min Range: -4.2765
Max Act: 3.9640. Min Act: -0.1700
Data Index: 3777572 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2765. Min Range: -4.2765
Max Act: 3.9327. Min Act: -0.1700
Data Index: 6534131 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19