Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6143 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.9464. Min Act: -0.1700
Data Index: 2373431 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.7589. Min Act: -0.1700
Data Index: 7262365 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.7277. Min Act: -0.1700
Data Index: 1013361 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.7589. Min Act: -0.1700
Data Index: 778047 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.6652. Min Act: -0.1700
Data Index: 2440164 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.6652. Min Act: -0.1700
Data Index: 4153557 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.6339. Min Act: -0.1700
Data Index: 4285547 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.6027. Min Act: -0.1700
Data Index: 8137337 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.5714. Min Act: -0.1700
Data Index: 5864478 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.5402. Min Act: -0.1700
Data Index: 5061510 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.5402. Min Act: -0.1700
Data Index: 6498295 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.5402. Min Act: -0.1700
Data Index: 4442353 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.5402. Min Act: -0.1700
Data Index: 2500339 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.5402. Min Act: -0.1700
Data Index: 6550000 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.5402. Min Act: -0.1700
Data Index: 667363 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.5089. Min Act: -0.1700
Data Index: 63360 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.5089. Min Act: -0.1700
Data Index: 4373173 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.4777. Min Act: -0.1700
Data Index: 1942232 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.4152. Min Act: -0.1700
Data Index: 2892571 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9464. Min Range: -6.9464
Max Act: 6.3839. Min Act: -0.1700
Data Index: 5719322 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19