Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4984 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.5671. Min Act: -0.1700
Data Index: 236414 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.5046. Min Act: -0.1700
Data Index: 7541529 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.3484. Min Act: -0.1700
Data Index: 2394095 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.3484. Min Act: -0.1700
Data Index: 4191399 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.2546. Min Act: -0.1700
Data Index: 3211596 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.2546. Min Act: -0.1700
Data Index: 342981 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.2546. Min Act: -0.1700
Data Index: 7185015 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.1921. Min Act: -0.1700
Data Index: 4344278 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.2234. Min Act: -0.1700
Data Index: 2194176 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.2234. Min Act: -0.1700
Data Index: 4598124 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.1921. Min Act: -0.1700
Data Index: 1980596 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.2234. Min Act: -0.1700
Data Index: 2945653 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.1609. Min Act: -0.1700
Data Index: 6613424 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.1609. Min Act: -0.1700
Data Index: 2660914 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.1609. Min Act: -0.1700
Data Index: 1772450 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.1296. Min Act: -0.1700
Data Index: 5741844 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.1296. Min Act: -0.1700
Data Index: 3867755 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.1296. Min Act: -0.1700
Data Index: 8495546 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.0984. Min Act: -0.1700
Data Index: 3135101 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5671. Min Range: -5.5671
Max Act: 5.0984. Min Act: -0.1700
Data Index: 1183784 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19