Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 750 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.1310. Min Act: -0.1700
Data Index: 6609933 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.1310. Min Act: -0.1700
Data Index: 7300464 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 4460263 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 3141007 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 2954434 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9123. Min Act: -0.1700
Data Index: 781632 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 5192460 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 7627472 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 2335887 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 7789716 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8498. Min Act: -0.1700
Data Index: 3385839 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 8490495 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8498. Min Act: -0.1700
Data Index: 5192461 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8185. Min Act: -0.1700
Data Index: 7964690 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8185. Min Act: -0.1700
Data Index: 4570865 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8185. Min Act: -0.1700
Data Index: 1201093 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8185. Min Act: -0.1699
Data Index: 6257602 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.7873. Min Act: -0.1700
Data Index: 988158 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.7873. Min Act: -0.1700
Data Index: 4114664 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.7560. Min Act: -0.1700
Data Index: 4200728 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19