Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3874 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.8157. Min Act: -0.1700
Data Index: 1535115 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.7220. Min Act: -0.1700
Data Index: 1517210 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.6907. Min Act: -0.1700
Data Index: 5641503 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.6907. Min Act: -0.1700
Data Index: 6906762 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.6282. Min Act: -0.1700
Data Index: 7438329 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.5970. Min Act: -0.1700
Data Index: 1103645 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.5657. Min Act: -0.1700
Data Index: 7249863 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.5345. Min Act: -0.1700
Data Index: 3510543 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.5032. Min Act: -0.1700
Data Index: 8554137 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.5032. Min Act: -0.1700
Data Index: 7070580 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.4720. Min Act: -0.1700
Data Index: 502804 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.4407. Min Act: -0.1700
Data Index: 3356299 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.4407. Min Act: -0.1700
Data Index: 2368670 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.4095. Min Act: -0.1700
Data Index: 7688324 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.4095. Min Act: -0.1700
Data Index: 2509801 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.3782. Min Act: -0.1700
Data Index: 5635232 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.3782. Min Act: -0.1700
Data Index: 7217801 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.3470. Min Act: -0.1700
Data Index: 1524561 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.3470. Min Act: -0.1700
Data Index: 4705093 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8157. Min Range: -7.8157
Max Act: 7.3470. Min Act: -0.1700
Data Index: 1846059 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19