Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3273. Min Range: -5.3273
Max Act: 5.3273. Min Act: -0.1700
Data Index: 4451819 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3273. Min Range: -5.3273
Max Act: 5.2335. Min Act: -0.1700
Data Index: 6518594 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3273. Min Range: -5.3273
Max Act: 5.2335. Min Act: -0.1700
Data Index: 8687871 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3273. Min Range: -5.3273
Max Act: 5.1710. Min Act: -0.1700
Data Index: 6321665 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3273. Min Range: -5.3273
Max Act: 5.1398. Min Act: -0.1700
Data Index: 204123 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3273. Min Range: -5.3273
Max Act: 5.1398. Min Act: -0.1700
Data Index: 451589 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3273. Min Range: -5.3273
Max Act: 5.0460. Min Act: -0.1700
Data Index: 818814 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3273. Min Range: -5.3273
Max Act: 5.0148. Min Act: -0.1700
Data Index: 248837 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3273. Min Range: -5.3273
Max Act: 5.0148. Min Act: -0.1700
Data Index: 7010422 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3273. Min Range: -5.3273
Max Act: 4.9835. Min Act: -0.1700
Data Index: 3890277 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3273. Min Range: -5.3273
Max Act: 4.9835. Min Act: -0.1700
Data Index: 6062345 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3273. Min Range: -5.3273
Max Act: 4.9835. Min Act: -0.1700
Data Index: 3282243 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3273. Min Range: -5.3273
Max Act: 4.9835. Min Act: -0.1700
Data Index: 1594717 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3273. Min Range: -5.3273
Max Act: 4.9835. Min Act: -0.1700
Data Index: 1863651 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3273. Min Range: -5.3273
Max Act: 4.9835. Min Act: -0.1700
Data Index: 7276333 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3273. Min Range: -5.3273
Max Act: 4.9835. Min Act: -0.1700
Data Index: 4212 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3273. Min Range: -5.3273
Max Act: 4.9210. Min Act: -0.1700
Data Index: 804500 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3273. Min Range: -5.3273
Max Act: 4.9523. Min Act: -0.1700
Data Index: 6986490 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3273. Min Range: -5.3273
Max Act: 4.9523. Min Act: -0.1700
Data Index: 4208 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3273. Min Range: -5.3273
Max Act: 4.9523. Min Act: -0.1700
Data Index: 6621238 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19