Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2163 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3250. Min Range: -5.3250
Max Act: 5.3250. Min Act: -0.1700
Data Index: 7154100 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3250. Min Range: -5.3250
Max Act: 5.0750. Min Act: -0.1700
Data Index: 607010 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3250. Min Range: -5.3250
Max Act: 5.0125. Min Act: -0.1700
Data Index: 6197696 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3250. Min Range: -5.3250
Max Act: 5.0125. Min Act: -0.1700
Data Index: 4314205 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3250. Min Range: -5.3250
Max Act: 5.0125. Min Act: -0.1700
Data Index: 1430121 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.9500. Min Act: -0.1700
Data Index: 3286210 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.8875. Min Act: -0.1700
Data Index: 3374556 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.7937. Min Act: -0.1700
Data Index: 2988311 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.8250. Min Act: -0.1700
Data Index: 4681372 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.8562. Min Act: -0.1700
Data Index: 2889661 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.7625. Min Act: -0.1700
Data Index: 4314204 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.7312. Min Act: -0.1700
Data Index: 6327413 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.7312. Min Act: -0.1700
Data Index: 754683 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.7312. Min Act: -0.1700
Data Index: 6691243 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.7000. Min Act: -0.1700
Data Index: 1648089 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.6687. Min Act: -0.1700
Data Index: 2763764 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.6375. Min Act: -0.1700
Data Index: 6005044 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.6687. Min Act: -0.1700
Data Index: 6327418 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.6062. Min Act: -0.1700
Data Index: 4193057 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3250. Min Range: -5.3250
Max Act: 4.6687. Min Act: -0.1700
Data Index: 48342 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19