Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.3415. Min Act: -0.1700
Data Index: 7638853 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.2790. Min Act: -0.1700
Data Index: 4384504 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.2790. Min Act: -0.1700
Data Index: 2107984 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.2790. Min Act: -0.1700
Data Index: 2392840 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.2790. Min Act: -0.1700
Data Index: 7226736 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.1540. Min Act: -0.1700
Data Index: 7890106 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.1540. Min Act: -0.1700
Data Index: 1246977 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.0290. Min Act: -0.1700
Data Index: 3496909 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.0290. Min Act: -0.1700
Data Index: 998336 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.0290. Min Act: -0.1700
Data Index: 2070180 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.0290. Min Act: -0.1700
Data Index: 2197088 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.0290. Min Act: -0.1699
Data Index: 7336240 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3415. Min Range: -8.3415
Max Act: 8.0290. Min Act: -0.1700
Data Index: 214963 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3415. Min Range: -8.3415
Max Act: 7.8415. Min Act: -0.1700
Data Index: 7429501 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3415. Min Range: -8.3415
Max Act: 7.7790. Min Act: -0.1700
Data Index: 1682035 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3415. Min Range: -8.3415
Max Act: 7.7790. Min Act: -0.1700
Data Index: 5366486 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3415. Min Range: -8.3415
Max Act: 7.7790. Min Act: -0.1700
Data Index: 2954235 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3415. Min Range: -8.3415
Max Act: 7.7165. Min Act: -0.1700
Data Index: 50444 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3415. Min Range: -8.3415
Max Act: 7.7165. Min Act: -0.1700
Data Index: 5350173 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3415. Min Range: -8.3415
Max Act: 7.7165. Min Act: -0.1700
Data Index: 6191677 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19