Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 982 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.7133. Min Act: -0.1700
Data Index: 8362616 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.7133. Min Act: -0.1700
Data Index: 1416862 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.6820. Min Act: -0.1700
Data Index: 5367441 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.6508. Min Act: -0.1700
Data Index: 7280501 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.6508. Min Act: -0.1700
Data Index: 2500159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.6195. Min Act: -0.1700
Data Index: 1197406 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5570. Min Act: -0.1700
Data Index: 3474989 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5570. Min Act: -0.1700
Data Index: 8052751 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5570. Min Act: -0.1700
Data Index: 7313252 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5258. Min Act: -0.1700
Data Index: 7721458 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 5250184 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 7430618 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4320. Min Act: -0.1700
Data Index: 4496560 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 719189 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4008. Min Act: -0.1700
Data Index: 2853093 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4008. Min Act: -0.1700
Data Index: 1718787 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4008. Min Act: -0.1700
Data Index: 6202279 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3695. Min Act: -0.1700
Data Index: 402187 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4008. Min Act: -0.1700
Data Index: 4670497 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3070. Min Act: -0.1700
Data Index: 7131480 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19