Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.9778. Min Act: -0.1700
Data Index: 573116 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.8215. Min Act: -0.1700
Data Index: 8601091 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.8528. Min Act: -0.1700
Data Index: 5238288 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7589. Min Act: -0.1700
Data Index: 2507175 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7902. Min Act: -0.1700
Data Index: 1288196 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7902. Min Act: -0.1700
Data Index: 6579911 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7902. Min Act: -0.1700
Data Index: 1930150 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7902. Min Act: -0.1700
Data Index: 3521247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7589. Min Act: -0.1700
Data Index: 434020 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7277. Min Act: -0.1700
Data Index: 6103582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7589. Min Act: -0.1700
Data Index: 5321594 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7589. Min Act: -0.1700
Data Index: 6613005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7589. Min Act: -0.1700
Data Index: 8092123 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7589. Min Act: -0.1700
Data Index: 8250461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7589. Min Act: -0.1700
Data Index: 811138 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7589. Min Act: -0.1700
Data Index: 222384 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7589. Min Act: -0.1700
Data Index: 4252818 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7589. Min Act: -0.1700
Data Index: 671107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7589. Min Act: -0.1700
Data Index: 8498230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9778. Min Range: -3.9778
Max Act: 3.7589. Min Act: -0.1700
Data Index: 4915747 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19