Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4736 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.8086. Min Act: -0.1700
Data Index: 8588143 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.6523. Min Act: -0.1700
Data Index: 5885915 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.4023. Min Act: -0.1700
Data Index: 2500920 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.3711. Min Act: -0.1700
Data Index: 8611207 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.3711. Min Act: -0.1700
Data Index: 8477755 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.3086. Min Act: -0.1700
Data Index: 3189897 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.3086. Min Act: -0.1700
Data Index: 682621 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.3086. Min Act: -0.1700
Data Index: 5713923 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.3086. Min Act: -0.1700
Data Index: 7363865 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.3086. Min Act: -0.1700
Data Index: 5091465 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.2773. Min Act: -0.1700
Data Index: 4571059 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.2148. Min Act: -0.1700
Data Index: 5463577 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.2148. Min Act: -0.1700
Data Index: 2730153 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.1523. Min Act: -0.1700
Data Index: 1007800 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.1836. Min Act: -0.1700
Data Index: 5471690 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.0898. Min Act: -0.1700
Data Index: 2146336 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.0898. Min Act: -0.1700
Data Index: 7108315 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.0586. Min Act: -0.1700
Data Index: 7401364 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8086. Min Range: -7.8086
Max Act: 6.9961. Min Act: -0.1700
Data Index: 6109871 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8086. Min Range: -7.8086
Max Act: 7.0586. Min Act: -0.1700
Data Index: 6286685 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19