Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3707 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.4727. Min Act: -0.1700
Data Index: 1737820 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.4414. Min Act: -0.1700
Data Index: 7561318 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.4414. Min Act: -0.1700
Data Index: 7583153 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3789. Min Act: -0.1700
Data Index: 3606199 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3789. Min Act: -0.1700
Data Index: 4373074 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3477. Min Act: -0.1700
Data Index: 3858181 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3477. Min Act: -0.1700
Data Index: 201934 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3477. Min Act: -0.1700
Data Index: 4616609 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3477. Min Act: -0.1700
Data Index: 1894864 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3477. Min Act: -0.1700
Data Index: 2761791 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3477. Min Act: -0.1700
Data Index: 8794008 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3477. Min Act: -0.1700
Data Index: 8385405 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3477. Min Act: -0.1700
Data Index: 490923 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3477. Min Act: -0.1700
Data Index: 6833194 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3477. Min Act: -0.1700
Data Index: 4102838 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3477. Min Act: -0.1700
Data Index: 6373731 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3164. Min Act: -0.1700
Data Index: 1744419 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3164. Min Act: -0.1700
Data Index: 1903374 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3164. Min Act: -0.1700
Data Index: 1989685 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3164. Min Act: -0.1700
Data Index: 3618454 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19