Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1317 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.9536. Min Act: -0.1700
Data Index: 4301924 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.9366. Min Act: -0.1700
Data Index: 6798781 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.9366. Min Act: -0.1700
Data Index: 7105601 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.9196. Min Act: -0.1700
Data Index: 1054408 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8855. Min Act: -0.1700
Data Index: 1159854 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8684. Min Act: -0.1700
Data Index: 1679872 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8855. Min Act: -0.1700
Data Index: 5428944 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.9026. Min Act: -0.1700
Data Index: 2387933 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8855. Min Act: -0.1700
Data Index: 2587663 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8684. Min Act: -0.1700
Data Index: 4072848 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8684. Min Act: -0.1700
Data Index: 1775489 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8684. Min Act: -0.1700
Data Index: 4951690 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8684. Min Act: -0.1700
Data Index: 1748521 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8684. Min Act: -0.1700
Data Index: 4055548 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8684. Min Act: -0.1700
Data Index: 8675335 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8684. Min Act: -0.1700
Data Index: 7468593 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8513. Min Act: -0.1700
Data Index: 7281600 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8684. Min Act: -0.1700
Data Index: 2723057 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8684. Min Act: -0.1700
Data Index: 7105600 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9536. Min Range: -1.9536
Max Act: 1.8342. Min Act: -0.1700
Data Index: 2818625 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19