Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2659 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.9202. Min Act: -0.1700
Data Index: 129800 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.7952. Min Act: -0.1700
Data Index: 1651109 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.5452. Min Act: -0.1700
Data Index: 4684538 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.5452. Min Act: -0.1700
Data Index: 4936080 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.4827. Min Act: -0.1700
Data Index: 2178593 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.4202. Min Act: -0.1700
Data Index: 2019609 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.2952. Min Act: -0.1700
Data Index: 4892466 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.2952. Min Act: -0.1700
Data Index: 784624 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.2952. Min Act: -0.1700
Data Index: 242188 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.2327. Min Act: -0.1700
Data Index: 91888 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.2327. Min Act: -0.1700
Data Index: 3704725 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.1702. Min Act: -0.1700
Data Index: 2093123 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.1702. Min Act: -0.1700
Data Index: 3638444 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.1702. Min Act: -0.1700
Data Index: 2080445 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.2327. Min Act: -0.1700
Data Index: 5006203 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.1702. Min Act: -0.1700
Data Index: 2597617 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.1702. Min Act: -0.1700
Data Index: 4746963 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.1702. Min Act: -0.1700
Data Index: 3581781 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.1077. Min Act: -0.1700
Data Index: 1044565 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9202. Min Range: -11.9202
Max Act: 11.1077. Min Act: -0.1700
Data Index: 1318842 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19