Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6167 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4352. Min Range: -7.4352
Max Act: 7.4352. Min Act: -0.1700
Data Index: 1190810 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4352. Min Range: -7.4352
Max Act: 7.2477. Min Act: -0.1700
Data Index: 1927184 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4352. Min Range: -7.4352
Max Act: 7.2164. Min Act: -0.1700
Data Index: 8221106 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4352. Min Range: -7.4352
Max Act: 7.0914. Min Act: -0.1700
Data Index: 434706 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4352. Min Range: -7.4352
Max Act: 7.0914. Min Act: -0.1700
Data Index: 6842928 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4352. Min Range: -7.4352
Max Act: 7.0602. Min Act: -0.1700
Data Index: 1976825 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4352. Min Range: -7.4352
Max Act: 7.0602. Min Act: -0.1700
Data Index: 4221259 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4352. Min Range: -7.4352
Max Act: 7.0289. Min Act: -0.1700
Data Index: 7903677 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4352. Min Range: -7.4352
Max Act: 6.9977. Min Act: -0.1700
Data Index: 8098036 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4352. Min Range: -7.4352
Max Act: 6.9664. Min Act: -0.1700
Data Index: 1169364 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4352. Min Range: -7.4352
Max Act: 6.9664. Min Act: -0.1700
Data Index: 6403766 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4352. Min Range: -7.4352
Max Act: 6.9352. Min Act: -0.1700
Data Index: 1661306 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4352. Min Range: -7.4352
Max Act: 6.9664. Min Act: -0.1700
Data Index: 6608559 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4352. Min Range: -7.4352
Max Act: 6.9352. Min Act: -0.1700
Data Index: 7858901 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4352. Min Range: -7.4352
Max Act: 6.9039. Min Act: -0.1700
Data Index: 3988497 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4352. Min Range: -7.4352
Max Act: 6.8727. Min Act: -0.1700
Data Index: 4200957 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4352. Min Range: -7.4352
Max Act: 6.8414. Min Act: -0.1700
Data Index: 1699294 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4352. Min Range: -7.4352
Max Act: 6.8414. Min Act: -0.1700
Data Index: 3560503 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4352. Min Range: -7.4352
Max Act: 6.8102. Min Act: -0.1700
Data Index: 6258830 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4352. Min Range: -7.4352
Max Act: 6.8102. Min Act: -0.1700
Data Index: 5615849 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19