Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2800 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.7392. Min Act: -0.1700
Data Index: 2676851 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.4267. Min Act: -0.1700
Data Index: 3398882 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.3017. Min Act: -0.1700
Data Index: 5462430 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.2392. Min Act: -0.1700
Data Index: 3175757 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.2392. Min Act: -0.1700
Data Index: 5126189 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.2392. Min Act: -0.1700
Data Index: 206228 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.1767. Min Act: -0.1700
Data Index: 3660070 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.1142. Min Act: -0.1700
Data Index: 6435186 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.1142. Min Act: -0.1700
Data Index: 6107253 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.1767. Min Act: -0.1700
Data Index: 8124781 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.1767. Min Act: -0.1700
Data Index: 4298459 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.1767. Min Act: -0.1700
Data Index: 77887 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.1142. Min Act: -0.1700
Data Index: 2992174 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.1142. Min Act: -0.1700
Data Index: 7931189 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.1142. Min Act: -0.1700
Data Index: 6671231 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.1767. Min Act: -0.1700
Data Index: 2965020 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.0517. Min Act: -0.1700
Data Index: 5837274 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.0517. Min Act: -0.1700
Data Index: 2264909 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7392. Min Range: -9.7392
Max Act: 9.0517. Min Act: -0.1700
Data Index: 3500185 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7392. Min Range: -9.7392
Max Act: 8.9892. Min Act: -0.1700
Data Index: 2310369 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19