Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4650 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.8648. Min Act: -0.1700
Data Index: 6093608 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.5523. Min Act: -0.1700
Data Index: 5397344 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.5523. Min Act: -0.1700
Data Index: 35659 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.5210. Min Act: -0.1700
Data Index: 5902438 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.5210. Min Act: -0.1700
Data Index: 7583046 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.5210. Min Act: -0.1700
Data Index: 811161 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.5210. Min Act: -0.1700
Data Index: 1533592 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.4898. Min Act: -0.1700
Data Index: 6297905 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.4898. Min Act: -0.1700
Data Index: 3211320 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.4898. Min Act: -0.1700
Data Index: 6961829 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.4898. Min Act: -0.1700
Data Index: 121668 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.4585. Min Act: -0.1700
Data Index: 8259006 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.4585. Min Act: -0.1700
Data Index: 2773881 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.4273. Min Act: -0.1700
Data Index: 2829733 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.3960. Min Act: -0.1700
Data Index: 6106204 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.3960. Min Act: -0.1700
Data Index: 1319605 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.4273. Min Act: -0.1700
Data Index: 633385 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.3960. Min Act: -0.1700
Data Index: 4587385 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.4273. Min Act: -0.1700
Data Index: 3833435 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8648. Min Range: -4.8648
Max Act: 4.4273. Min Act: -0.1700
Data Index: 7931111 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19