Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1528 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1564. Min Range: -2.1564
Max Act: 2.1564. Min Act: -0.1700
Data Index: 4967474 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.9547. Min Act: -0.1698
Data Index: 6893211 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.9377. Min Act: -0.1700
Data Index: 7971708 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8524. Min Act: -0.1700
Data Index: 8184621 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8866. Min Act: -0.1700
Data Index: 2497803 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8866. Min Act: -0.1698
Data Index: 3037592 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8866. Min Act: -0.1697
Data Index: 6794499 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.9037. Min Act: -0.1699
Data Index: 3277223 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8695. Min Act: -0.1700
Data Index: 7292562 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8695. Min Act: -0.1700
Data Index: 6539242 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8695. Min Act: -0.1700
Data Index: 8516220 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8695. Min Act: -0.1700
Data Index: 3871294 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8524. Min Act: -0.1700
Data Index: 7292560 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8695. Min Act: -0.1688
Data Index: 1047867 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8695. Min Act: -0.1700
Data Index: 6909201 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8695. Min Act: -0.1700
Data Index: 4912661 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8695. Min Act: -0.1700
Data Index: 6868058 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8695. Min Act: -0.1699
Data Index: 6446652 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8524. Min Act: -0.1700
Data Index: 2589437 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1564. Min Range: -2.1564
Max Act: 1.8524. Min Act: -0.1700
Data Index: 6256392 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19