Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 829 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9439. Min Act: -0.1700
Data Index: 3174361 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9126. Min Act: -0.1700
Data Index: 8035315 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9126. Min Act: -0.1700
Data Index: 5900765 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9126. Min Act: -0.1700
Data Index: 3968504 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9126. Min Act: -0.1700
Data Index: 8753427 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9126. Min Act: -0.1700
Data Index: 3633116 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9126. Min Act: -0.1700
Data Index: 5075316 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.8813. Min Act: -0.1700
Data Index: 424876 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.8813. Min Act: -0.1700
Data Index: 5126109 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9126. Min Act: -0.1700
Data Index: 2444379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9126. Min Act: -0.1700
Data Index: 2631408 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9126. Min Act: -0.1700
Data Index: 6436953 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.9126. Min Act: -0.1700
Data Index: 6650029 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.8813. Min Act: -0.1700
Data Index: 7521195 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.8813. Min Act: -0.1699
Data Index: 7105462 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.8813. Min Act: -0.1700
Data Index: 3273128 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.8813. Min Act: -0.1700
Data Index: 7129857 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.8813. Min Act: -0.1700
Data Index: 318928 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.8813. Min Act: -0.1700
Data Index: 5004923 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9439. Min Range: -3.9439
Max Act: 3.8813. Min Act: -0.1700
Data Index: 4642532 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19