Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2857 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.0178. Min Range: -16.0178
Max Act: 16.0178. Min Act: -0.1700
Data Index: 4280416 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.5803. Min Act: -0.1700
Data Index: 7223623 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.4553. Min Act: -0.1700
Data Index: 6592196 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.3928. Min Act: -0.1700
Data Index: 1777516 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.3303. Min Act: -0.1700
Data Index: 1656271 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.3303. Min Act: -0.1700
Data Index: 1282915 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.3303. Min Act: -0.1700
Data Index: 2710070 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.2678. Min Act: -0.1700
Data Index: 4685205 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.2678. Min Act: -0.1700
Data Index: 2527439 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.2053. Min Act: -0.1700
Data Index: 266960 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.2053. Min Act: -0.1700
Data Index: 1574165 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.2053. Min Act: -0.1700
Data Index: 1456239 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.1428. Min Act: -0.1700
Data Index: 1283221 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.1428. Min Act: -0.1700
Data Index: 1537552 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.0803. Min Act: -0.1700
Data Index: 6654820 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.0803. Min Act: -0.1700
Data Index: 2414892 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.0803. Min Act: -0.1700
Data Index: 6408046 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.0178. Min Act: -0.1700
Data Index: 1545532 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.0178. Min Act: -0.1700
Data Index: 3374481 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.0178. Min Range: -16.0178
Max Act: 15.0178. Min Act: -0.1700
Data Index: 396418 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19