Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2948 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.9312. Min Act: -0.1700
Data Index: 2050770 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.8995. Min Act: -0.1700
Data Index: 1565961 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.8677. Min Act: -0.1700
Data Index: 3419554 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.8518. Min Act: -0.1700
Data Index: 8149143 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7882. Min Act: -0.1700
Data Index: 5659660 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.8041. Min Act: -0.1700
Data Index: 7577708 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7882. Min Act: -0.1700
Data Index: 2539458 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7723. Min Act: -0.1700
Data Index: 7951343 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7563. Min Act: -0.1700
Data Index: 3902516 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7723. Min Act: -0.1700
Data Index: 4044029 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7723. Min Act: -0.1700
Data Index: 5034685 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7882. Min Act: -0.1700
Data Index: 8467572 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7882. Min Act: -0.1700
Data Index: 741027 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7723. Min Act: -0.1700
Data Index: 432313 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7563. Min Act: -0.1700
Data Index: 2554582 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7563. Min Act: -0.1700
Data Index: 2034106 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7723. Min Act: -0.1700
Data Index: 4678224 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7403. Min Act: -0.1700
Data Index: 1173646 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7723. Min Act: -0.1700
Data Index: 1420952 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9312. Min Range: -2.9312
Max Act: 2.7563. Min Act: -0.1700
Data Index: 7850467 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19