Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0402. Min Range: -5.0402
Max Act: 5.0402. Min Act: -0.1700
Data Index: 5488670 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.9464. Min Act: -0.1700
Data Index: 7749162 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.9152. Min Act: -0.1700
Data Index: 8600603 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.9464. Min Act: -0.1700
Data Index: 1579743 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.8839. Min Act: -0.1700
Data Index: 6736270 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.8214. Min Act: -0.1700
Data Index: 1711417 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.8214. Min Act: -0.1700
Data Index: 270400 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.8214. Min Act: -0.1700
Data Index: 552121 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.8214. Min Act: -0.1700
Data Index: 5669713 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.8214. Min Act: -0.1700
Data Index: 1144865 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.7902. Min Act: -0.1700
Data Index: 6328172 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.7589. Min Act: -0.1700
Data Index: 8520352 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.7277. Min Act: -0.1700
Data Index: 6826134 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.7277. Min Act: -0.1700
Data Index: 6224021 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.7277. Min Act: -0.1700
Data Index: 2638444 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.6652. Min Act: -0.1700
Data Index: 1354293 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.6652. Min Act: -0.1700
Data Index: 2973272 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.6652. Min Act: -0.1700
Data Index: 6689055 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.6652. Min Act: -0.1700
Data Index: 5423002 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0402. Min Range: -5.0402
Max Act: 4.6339. Min Act: -0.1700
Data Index: 10996 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19