Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1315 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0569. Min Range: -4.0569
Max Act: 4.0569. Min Act: -0.1700
Data Index: 393943 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.9944. Min Act: -0.1700
Data Index: 8251787 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.9319. Min Act: -0.1700
Data Index: 7617559 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.9319. Min Act: -0.1700
Data Index: 7723470 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.9006. Min Act: -0.1700
Data Index: 2331046 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.9006. Min Act: -0.1700
Data Index: 3005423 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.8694. Min Act: -0.1700
Data Index: 7509337 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.9006. Min Act: -0.1700
Data Index: 250178 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.8694. Min Act: -0.1700
Data Index: 4244465 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.8694. Min Act: -0.1700
Data Index: 8192033 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.8694. Min Act: -0.1700
Data Index: 1282874 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.8381. Min Act: -0.1700
Data Index: 2881768 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.8381. Min Act: -0.1700
Data Index: 521946 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.8694. Min Act: -0.1700
Data Index: 3764006 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.8381. Min Act: -0.1700
Data Index: 1898855 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.8381. Min Act: -0.1700
Data Index: 6642070 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.8068. Min Act: -0.1700
Data Index: 1561143 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.7756. Min Act: -0.1700
Data Index: 8041324 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.7756. Min Act: -0.1700
Data Index: 6568563 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0569. Min Range: -4.0569
Max Act: 3.8068. Min Act: -0.1700
Data Index: 5250621 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19