Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3160 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6888. Min Range: -9.6888
Max Act: 9.6888. Min Act: -0.1700
Data Index: 5497606 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6888. Min Range: -9.6888
Max Act: 9.4388. Min Act: -0.1700
Data Index: 353234 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6888. Min Range: -9.6888
Max Act: 9.2513. Min Act: -0.1700
Data Index: 1654602 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6888. Min Range: -9.6888
Max Act: 9.2513. Min Act: -0.1700
Data Index: 7811047 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6888. Min Range: -9.6888
Max Act: 9.0638. Min Act: -0.1700
Data Index: 1586434 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6888. Min Range: -9.6888
Max Act: 9.0013. Min Act: -0.1700
Data Index: 8456553 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6888. Min Range: -9.6888
Max Act: 9.0013. Min Act: -0.1700
Data Index: 2052180 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6888. Min Range: -9.6888
Max Act: 8.8138. Min Act: -0.1700
Data Index: 7722454 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6888. Min Range: -9.6888
Max Act: 8.6263. Min Act: -0.1700
Data Index: 7297790 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6888. Min Range: -9.6888
Max Act: 8.5638. Min Act: -0.1700
Data Index: 8544588 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6888. Min Range: -9.6888
Max Act: 7.9700. Min Act: -0.1700
Data Index: 5986362 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6888. Min Range: -9.6888
Max Act: 7.8450. Min Act: -0.1700
Data Index: 7809015 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6888. Min Range: -9.6888
Max Act: 7.8138. Min Act: -0.1700
Data Index: 5322232 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6888. Min Range: -9.6888
Max Act: 7.7513. Min Act: -0.1700
Data Index: 664563 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6888. Min Range: -9.6888
Max Act: 7.7513. Min Act: -0.1700
Data Index: 2961715 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6888. Min Range: -9.6888
Max Act: 7.6888. Min Act: -0.1700
Data Index: 8060374 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6888. Min Range: -9.6888
Max Act: 7.6575. Min Act: -0.1700
Data Index: 83331 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6888. Min Range: -9.6888
Max Act: 7.5950. Min Act: -0.1700
Data Index: 368617 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6888. Min Range: -9.6888
Max Act: 7.5325. Min Act: -0.1700
Data Index: 8171285 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6888. Min Range: -9.6888
Max Act: 7.5325. Min Act: -0.1700
Data Index: 2192186 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19