Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4139 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.2057. Min Act: -0.1700
Data Index: 4101928 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.1745. Min Act: -0.1700
Data Index: 8453056 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.0807. Min Act: -0.1700
Data Index: 6301170 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.0495. Min Act: -0.1700
Data Index: 4862618 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.0495. Min Act: -0.1700
Data Index: 1145097 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2057. Min Range: -6.2057
Max Act: 6.0182. Min Act: -0.1700
Data Index: 4213173 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9557. Min Act: -0.1700
Data Index: 7097990 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9557. Min Act: -0.1700
Data Index: 8406510 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.9245. Min Act: -0.1700
Data Index: 7232447 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8932. Min Act: -0.1700
Data Index: 7097991 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8620. Min Act: -0.1700
Data Index: 988614 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8932. Min Act: -0.1700
Data Index: 7969100 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8620. Min Act: -0.1700
Data Index: 8433173 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8307. Min Act: -0.1700
Data Index: 2427491 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.8307. Min Act: -0.1700
Data Index: 5576733 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7995. Min Act: -0.1700
Data Index: 2177939 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7995. Min Act: -0.1700
Data Index: 70678 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7995. Min Act: -0.1700
Data Index: 451436 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7995. Min Act: -0.1700
Data Index: 6215547 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2057. Min Range: -6.2057
Max Act: 5.7995. Min Act: -0.1700
Data Index: 1434452 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19