Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4877 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.6674. Min Act: -0.1700
Data Index: 3711139 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.4174. Min Act: -0.1700
Data Index: 6004151 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.2924. Min Act: -0.1700
Data Index: 3341514 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.2924. Min Act: -0.1700
Data Index: 6066164 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.2611. Min Act: -0.1700
Data Index: 1791077 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1986. Min Act: -0.1700
Data Index: 5357446 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1361. Min Act: -0.1700
Data Index: 3341513 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1674. Min Act: -0.1700
Data Index: 2304561 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1674. Min Act: -0.1700
Data Index: 4981193 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1361. Min Act: -0.1700
Data Index: 8607917 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1674. Min Act: -0.1700
Data Index: 8735022 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1361. Min Act: -0.1700
Data Index: 580110 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1361. Min Act: -0.1700
Data Index: 3002241 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1361. Min Act: -0.1700
Data Index: 4464263 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1361. Min Act: -0.1700
Data Index: 6413233 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1361. Min Act: -0.1700
Data Index: 8618590 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1049. Min Act: -0.1700
Data Index: 8287548 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.1049. Min Act: -0.1700
Data Index: 8283108 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.0424. Min Act: -0.1700
Data Index: 2713872 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6674. Min Range: -6.6674
Max Act: 6.0736. Min Act: -0.1700
Data Index: 3777051 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19