Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2655 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.1908. Min Act: -0.1700
Data Index: 905141 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.1595. Min Act: -0.1700
Data Index: 4933319 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.1283. Min Act: -0.1700
Data Index: 3174822 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.1283. Min Act: -0.1700
Data Index: 4690195 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0658. Min Act: -0.1700
Data Index: 5014780 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0658. Min Act: -0.1700
Data Index: 4490044 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0345. Min Act: -0.1700
Data Index: 2851003 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0345. Min Act: -0.1700
Data Index: 4055246 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0345. Min Act: -0.1700
Data Index: 4667930 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0345. Min Act: -0.1700
Data Index: 1983294 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0345. Min Act: -0.1700
Data Index: 4241240 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0345. Min Act: -0.1700
Data Index: 1278846 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0345. Min Act: -0.1700
Data Index: 485088 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1908. Min Range: -5.1908
Max Act: 5.0033. Min Act: -0.1700
Data Index: 8290606 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1908. Min Range: -5.1908
Max Act: 4.9720. Min Act: -0.1700
Data Index: 2344529 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1908. Min Range: -5.1908
Max Act: 4.9408. Min Act: -0.1700
Data Index: 3545074 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1908. Min Range: -5.1908
Max Act: 4.9408. Min Act: -0.1700
Data Index: 810975 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1908. Min Range: -5.1908
Max Act: 4.9408. Min Act: -0.1700
Data Index: 1736511 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1908. Min Range: -5.1908
Max Act: 4.9095. Min Act: -0.1700
Data Index: 3301410 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1908. Min Range: -5.1908
Max Act: 4.9095. Min Act: -0.1700
Data Index: 7452194 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19