Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 892 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0164. Min Range: -6.0164
Max Act: 6.0164. Min Act: -0.1700
Data Index: 4174525 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0164. Min Range: -6.0164
Max Act: 6.0164. Min Act: -0.1700
Data Index: 3798084 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.9852. Min Act: -0.1700
Data Index: 6628911 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.9852. Min Act: -0.1700
Data Index: 6760421 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.9539. Min Act: -0.1700
Data Index: 5195795 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.9539. Min Act: -0.1700
Data Index: 667128 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.9539. Min Act: -0.1700
Data Index: 8623645 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.8914. Min Act: -0.1700
Data Index: 1966677 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.8914. Min Act: -0.1700
Data Index: 3150450 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.8914. Min Act: -0.1700
Data Index: 5325459 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.8602. Min Act: -0.1700
Data Index: 8438464 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.8914. Min Act: -0.1700
Data Index: 3814187 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.8289. Min Act: -0.1700
Data Index: 2703823 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.8289. Min Act: -0.1700
Data Index: 4530353 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.7977. Min Act: -0.1700
Data Index: 3924804 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.8289. Min Act: -0.1700
Data Index: 563216 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.8289. Min Act: -0.1700
Data Index: 2130136 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.7977. Min Act: -0.1700
Data Index: 117263 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.7977. Min Act: -0.1700
Data Index: 1037457 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0164. Min Range: -6.0164
Max Act: 5.7977. Min Act: -0.1700
Data Index: 2644385 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19