Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5003 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1530. Min Range: -5.1530
Max Act: 5.1217. Min Act: -0.1700
Data Index: 8492672 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1530. Min Range: -5.1530
Max Act: 5.1530. Min Act: -0.1700
Data Index: 394782 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1530. Min Range: -5.1530
Max Act: 5.1217. Min Act: -0.1700
Data Index: 2116806 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1530. Min Range: -5.1530
Max Act: 5.0592. Min Act: -0.1700
Data Index: 4283669 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1530. Min Range: -5.1530
Max Act: 5.1217. Min Act: -0.1700
Data Index: 8172311 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1530. Min Range: -5.1530
Max Act: 5.0592. Min Act: -0.1700
Data Index: 8183407 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1530. Min Range: -5.1530
Max Act: 5.0280. Min Act: -0.1700
Data Index: 4957280 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.9655. Min Act: -0.1700
Data Index: 6327374 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.9655. Min Act: -0.1700
Data Index: 7208098 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.9342. Min Act: -0.1700
Data Index: 872913 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.9342. Min Act: -0.1700
Data Index: 5942905 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.9030. Min Act: -0.1700
Data Index: 8682941 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.8717. Min Act: -0.1700
Data Index: 8025775 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.8717. Min Act: -0.1700
Data Index: 1934006 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.8717. Min Act: -0.1700
Data Index: 6166816 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.8405. Min Act: -0.1700
Data Index: 7275365 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.8092. Min Act: -0.1700
Data Index: 964188 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.8092. Min Act: -0.1700
Data Index: 8143095 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.8092. Min Act: -0.1700
Data Index: 7524084 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1530. Min Range: -5.1530
Max Act: 4.8405. Min Act: -0.1700
Data Index: 3006122 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19