Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1923 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.6213. Min Act: -0.1700
Data Index: 5699003 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.5900. Min Act: -0.1700
Data Index: 8680261 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.5588. Min Act: -0.1700
Data Index: 3411337 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.4650. Min Act: -0.1700
Data Index: 4828948 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.4338. Min Act: -0.1700
Data Index: 1732640 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.3088. Min Act: -0.1700
Data Index: 3659929 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.2775. Min Act: -0.1700
Data Index: 1170318 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.2463. Min Act: -0.1700
Data Index: 6280392 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.2150. Min Act: -0.1700
Data Index: 7795336 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.1525. Min Act: -0.1700
Data Index: 2993835 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.1838. Min Act: -0.1700
Data Index: 6873891 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.1525. Min Act: -0.1700
Data Index: 6222791 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.1525. Min Act: -0.1700
Data Index: 482009 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.1525. Min Act: -0.1700
Data Index: 4684584 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.1525. Min Act: -0.1700
Data Index: 7771360 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.1525. Min Act: -0.1700
Data Index: 7836339 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.1838. Min Act: -0.1700
Data Index: 8754226 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.1213. Min Act: -0.1700
Data Index: 3293949 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.1213. Min Act: -0.1700
Data Index: 2994552 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6213. Min Range: -6.6213
Max Act: 6.1525. Min Act: -0.1700
Data Index: 5724789 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19