Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.5245. Min Act: -0.1700
Data Index: 2896035 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.4759. Min Act: -0.1700
Data Index: 8017633 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.4759. Min Act: -0.1700
Data Index: 7662742 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.4434. Min Act: -0.1700
Data Index: 221657 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.4271. Min Act: -0.1700
Data Index: 8681282 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.3945. Min Act: -0.1700
Data Index: 5838249 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.3945. Min Act: -0.1700
Data Index: 6996117 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.3618. Min Act: -0.1700
Data Index: 1857185 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.3618. Min Act: -0.1700
Data Index: 4864379 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.3290. Min Act: -0.1700
Data Index: 6148934 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.3126. Min Act: -0.1700
Data Index: 609829 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.3454. Min Act: -0.1700
Data Index: 5271064 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.3290. Min Act: -0.1700
Data Index: 30383 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.3126. Min Act: -0.1700
Data Index: 8175742 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.3126. Min Act: -0.1700
Data Index: 5994699 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.2796. Min Act: -0.1700
Data Index: 1825558 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.2796. Min Act: -0.1700
Data Index: 2202213 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.2796. Min Act: -0.1700
Data Index: 2821700 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.2632. Min Act: -0.1700
Data Index: 829909 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5245. Min Range: -2.5245
Max Act: 2.2301. Min Act: -0.1700
Data Index: 850798 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19