Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5557 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.4408. Min Act: -0.1700
Data Index: 5073027 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.3783. Min Act: -0.1700
Data Index: 1893032 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.3783. Min Act: -0.1700
Data Index: 8752907 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.3783. Min Act: -0.1700
Data Index: 5308943 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.3471. Min Act: -0.1700
Data Index: 8783961 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2846. Min Act: -0.1700
Data Index: 2282521 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2846. Min Act: -0.1700
Data Index: 5366293 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.3158. Min Act: -0.1700
Data Index: 1470340 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2846. Min Act: -0.1700
Data Index: 947567 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2533. Min Act: -0.1700
Data Index: 7839041 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2221. Min Act: -0.1700
Data Index: 5261 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2533. Min Act: -0.1700
Data Index: 3459984 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2221. Min Act: -0.1700
Data Index: 3640571 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2221. Min Act: -0.1700
Data Index: 1411509 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2221. Min Act: -0.1700
Data Index: 3581188 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2221. Min Act: -0.1700
Data Index: 3843413 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2221. Min Act: -0.1700
Data Index: 1902243 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2221. Min Act: -0.1700
Data Index: 4944643 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.1908. Min Act: -0.1700
Data Index: 6866773 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4408. Min Range: -6.4408
Max Act: 6.2221. Min Act: -0.1700
Data Index: 7559068 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19