Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.1004. Min Act: -0.1700
Data Index: 5099409 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.1316. Min Act: -0.1700
Data Index: 4939500 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.1004. Min Act: -0.1700
Data Index: 6403206 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.1004. Min Act: -0.1700
Data Index: 6871454 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.1004. Min Act: -0.1700
Data Index: 4034765 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.1004. Min Act: -0.1700
Data Index: 5003206 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0691. Min Act: -0.1700
Data Index: 6046832 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0691. Min Act: -0.1700
Data Index: 2517025 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0691. Min Act: -0.1700
Data Index: 7502986 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0691. Min Act: -0.1698
Data Index: 3871161 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0691. Min Act: -0.1700
Data Index: 4029573 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0378. Min Act: -0.1700
Data Index: 756871 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0378. Min Act: -0.1700
Data Index: 2325656 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0378. Min Act: -0.1700
Data Index: 4919340 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0378. Min Act: -0.1700
Data Index: 4676646 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0378. Min Act: -0.1700
Data Index: 4411777 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0378. Min Act: -0.1700
Data Index: 4250568 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0378. Min Act: -0.1700
Data Index: 4185785 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0378. Min Act: -0.1700
Data Index: 4120245 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.0378. Min Act: -0.1700
Data Index: 632479 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19