Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2857 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1324. Min Range: -5.1324
Max Act: 5.1324. Min Act: -0.1700
Data Index: 8724953 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1324. Min Range: -5.1324
Max Act: 5.0074. Min Act: -0.1700
Data Index: 504528 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1324. Min Range: -5.1324
Max Act: 5.0074. Min Act: -0.1700
Data Index: 3271564 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.9761. Min Act: -0.1700
Data Index: 7879544 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.9449. Min Act: -0.1700
Data Index: 7395568 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.9136. Min Act: -0.1700
Data Index: 5062335 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.9136. Min Act: -0.1700
Data Index: 4775205 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.9136. Min Act: -0.1700
Data Index: 6669245 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.8511. Min Act: -0.1700
Data Index: 6729053 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.8511. Min Act: -0.1700
Data Index: 5339820 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.8511. Min Act: -0.1700
Data Index: 7595175 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.8511. Min Act: -0.1700
Data Index: 1911862 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.8199. Min Act: -0.1700
Data Index: 1447302 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.7886. Min Act: -0.1700
Data Index: 7121894 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.7886. Min Act: -0.1700
Data Index: 7009928 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.7886. Min Act: -0.1700
Data Index: 3972367 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.7886. Min Act: -0.1700
Data Index: 6501365 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.7886. Min Act: -0.1700
Data Index: 387125 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.7574. Min Act: -0.1700
Data Index: 593089 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1324. Min Range: -5.1324
Max Act: 4.7574. Min Act: -0.1700
Data Index: 7083273 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19