Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4844 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1467. Min Range: -3.1467
Max Act: 3.1467. Min Act: -0.1700
Data Index: 306897 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1467. Min Range: -3.1467
Max Act: 3.0522. Min Act: -0.1700
Data Index: 1879393 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9890. Min Act: -0.1700
Data Index: 2408519 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9890. Min Act: -0.1700
Data Index: 803202 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9732. Min Act: -0.1700
Data Index: 306898 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9732. Min Act: -0.1700
Data Index: 1084947 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9732. Min Act: -0.1700
Data Index: 4652852 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9573. Min Act: -0.1700
Data Index: 2936445 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9732. Min Act: -0.1700
Data Index: 4949266 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9573. Min Act: -0.1700
Data Index: 4670965 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9257. Min Act: -0.1700
Data Index: 7926402 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9257. Min Act: -0.1700
Data Index: 8710805 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9257. Min Act: -0.1700
Data Index: 3630520 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9257. Min Act: -0.1700
Data Index: 1221563 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9257. Min Act: -0.1700
Data Index: 920518 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9098. Min Act: -0.1700
Data Index: 7643793 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9098. Min Act: -0.1700
Data Index: 963334 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.9098. Min Act: -0.1700
Data Index: 3674975 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.8940. Min Act: -0.1700
Data Index: 1879389 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1467. Min Range: -3.1467
Max Act: 2.8940. Min Act: -0.1700
Data Index: 4652853 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19