Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1717 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.5577. Min Act: -0.1700
Data Index: 7473946 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.5264. Min Act: -0.1700
Data Index: 4652618 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.5264. Min Act: -0.1700
Data Index: 2024655 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.5107. Min Act: -0.1700
Data Index: 5108682 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4951. Min Act: -0.1700
Data Index: 1607037 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4794. Min Act: -0.1700
Data Index: 1036464 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4951. Min Act: -0.1700
Data Index: 5110428 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4794. Min Act: -0.1700
Data Index: 4054676 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4951. Min Act: -0.1700
Data Index: 4897564 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4324. Min Act: -0.1700
Data Index: 6740820 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4481. Min Act: -0.1700
Data Index: 2505344 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4324. Min Act: -0.1700
Data Index: 5465504 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4324. Min Act: -0.1700
Data Index: 4328666 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4324. Min Act: -0.1700
Data Index: 2772842 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4324. Min Act: -0.1700
Data Index: 5680971 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4324. Min Act: -0.1700
Data Index: 5705443 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4481. Min Act: -0.1700
Data Index: 5926683 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4167. Min Act: -0.1700
Data Index: 6395201 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4324. Min Act: -0.1700
Data Index: 6654738 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5577. Min Range: -3.5577
Max Act: 3.4324. Min Act: -0.1700
Data Index: 5809922 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19