Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.9751. Min Act: -0.1700
Data Index: 3256746 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.9277. Min Act: -0.1700
Data Index: 6050463 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.9277. Min Act: -0.1700
Data Index: 1420213 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.9435. Min Act: -0.1700
Data Index: 1281825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.9277. Min Act: -0.1700
Data Index: 4586700 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.9277. Min Act: -0.1700
Data Index: 1836902 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8960. Min Act: -0.1700
Data Index: 5289264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8960. Min Act: -0.1700
Data Index: 3773837 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8960. Min Act: -0.1700
Data Index: 563611 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8960. Min Act: -0.1700
Data Index: 6286971 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8960. Min Act: -0.1700
Data Index: 522151 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8960. Min Act: -0.1700
Data Index: 1941414 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8960. Min Act: -0.1700
Data Index: 4197690 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8801. Min Act: -0.1700
Data Index: 3079199 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8801. Min Act: -0.1700
Data Index: 2661861 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8801. Min Act: -0.1700
Data Index: 1965586 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8801. Min Act: -0.1700
Data Index: 5492094 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8801. Min Act: -0.1700
Data Index: 3627620 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8801. Min Act: -0.1700
Data Index: 7993943 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9751. Min Range: -2.9751
Max Act: 2.8801. Min Act: -0.1700
Data Index: 3901166 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19