Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5685. Min Range: -6.5685
Max Act: 6.5685. Min Act: -0.1700
Data Index: 6770824 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5685. Min Range: -6.5685
Max Act: 6.2248. Min Act: -0.1700
Data Index: 3302631 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.6310. Min Act: -0.1700
Data Index: 8143760 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.6310. Min Act: -0.1700
Data Index: 2333799 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.5685. Min Act: -0.1700
Data Index: 6144124 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.5373. Min Act: -0.1700
Data Index: 6468074 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.5373. Min Act: -0.1700
Data Index: 6395416 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.5373. Min Act: -0.1700
Data Index: 4694752 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.4435. Min Act: -0.1700
Data Index: 1069444 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.4435. Min Act: -0.1700
Data Index: 4315618 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.3810. Min Act: -0.1700
Data Index: 6727073 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.3498. Min Act: -0.1700
Data Index: 33521 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.3498. Min Act: -0.1700
Data Index: 4023134 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.2873. Min Act: -0.1700
Data Index: 737146 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.3185. Min Act: -0.1700
Data Index: 2056154 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.2873. Min Act: -0.1700
Data Index: 6070567 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.2873. Min Act: -0.1700
Data Index: 4279968 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.2873. Min Act: -0.1700
Data Index: 8799683 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.2873. Min Act: -0.1700
Data Index: 6329325 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5685. Min Range: -6.5685
Max Act: 5.2560. Min Act: -0.1700
Data Index: 3101266 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19