Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1526 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.6825. Min Act: -0.1700
Data Index: 2775637 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.6512. Min Act: -0.1700
Data Index: 3770812 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.6669. Min Act: -0.1700
Data Index: 8467924 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.6200. Min Act: -0.1700
Data Index: 961296 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.6200. Min Act: -0.1700
Data Index: 3789851 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.6043. Min Act: -0.1700
Data Index: 2671657 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.5730. Min Act: -0.1700
Data Index: 7259584 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.5573. Min Act: -0.1700
Data Index: 6397743 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.5104. Min Act: -0.1700
Data Index: 398511 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.5260. Min Act: -0.1700
Data Index: 8449191 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.5104. Min Act: -0.1700
Data Index: 728366 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.5104. Min Act: -0.1700
Data Index: 7309538 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.4947. Min Act: -0.1700
Data Index: 6873168 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.5104. Min Act: -0.1700
Data Index: 5575165 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.4947. Min Act: -0.1700
Data Index: 8791276 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.4947. Min Act: -0.1700
Data Index: 4807164 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.4790. Min Act: -0.1700
Data Index: 4024136 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.4790. Min Act: -0.1700
Data Index: 1059473 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.4634. Min Act: -0.1700
Data Index: 1411491 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6825. Min Range: -3.6825
Max Act: 3.4477. Min Act: -0.1700
Data Index: 5805061 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19