Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2952 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.5494. Min Act: -0.1700
Data Index: 1344201 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.5494. Min Act: -0.1700
Data Index: 448143 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.5181. Min Act: -0.1700
Data Index: 3989309 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4869. Min Act: -0.1700
Data Index: 4143457 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.5181. Min Act: -0.1700
Data Index: 4267705 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.5181. Min Act: -0.1700
Data Index: 7708388 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.5181. Min Act: -0.1700
Data Index: 3268330 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.5181. Min Act: -0.1700
Data Index: 3044634 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4869. Min Act: -0.1700
Data Index: 3651674 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4869. Min Act: -0.1700
Data Index: 1154241 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4556. Min Act: -0.1700
Data Index: 2038638 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4556. Min Act: -0.1700
Data Index: 3253781 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4556. Min Act: -0.1700
Data Index: 1903823 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4556. Min Act: -0.1700
Data Index: 1784627 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4556. Min Act: -0.1700
Data Index: 3240657 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4556. Min Act: -0.1700
Data Index: 2147155 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4556. Min Act: -0.1700
Data Index: 3616 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4556. Min Act: -0.1700
Data Index: 1858840 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4556. Min Act: -0.1700
Data Index: 652255 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5494. Min Range: -4.5494
Max Act: 4.4244. Min Act: -0.1700
Data Index: 2661620 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19