Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1082 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.4504. Min Act: -0.1700
Data Index: 3055805 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.4817. Min Act: -0.1700
Data Index: 570656 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.4504. Min Act: -0.1700
Data Index: 4612115 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3879. Min Act: -0.1700
Data Index: 2537611 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3567. Min Act: -0.1700
Data Index: 2472087 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3879. Min Act: -0.1700
Data Index: 7943659 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3879. Min Act: -0.1700
Data Index: 8213508 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3567. Min Act: -0.1700
Data Index: 6038893 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3567. Min Act: -0.1700
Data Index: 1046801 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.2942. Min Act: -0.1700
Data Index: 1568957 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3254. Min Act: -0.1700
Data Index: 2450750 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3254. Min Act: -0.1700
Data Index: 3278149 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.2942. Min Act: -0.1700
Data Index: 5824030 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3254. Min Act: -0.1700
Data Index: 6572891 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3254. Min Act: -0.1700
Data Index: 1055425 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3254. Min Act: -0.1700
Data Index: 131427 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.2942. Min Act: -0.1700
Data Index: 553283 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.2942. Min Act: -0.1700
Data Index: 1074712 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.2942. Min Act: -0.1700
Data Index: 715297 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3254. Min Act: -0.1700
Data Index: 5910079 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19