Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3720 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.4533. Min Act: -0.1700
Data Index: 5173332 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.4100. Min Act: -0.1700
Data Index: 8744382 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3958. Min Act: -0.1700
Data Index: 5173328 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3611. Min Act: -0.1700
Data Index: 5173336 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3474. Min Act: -0.1700
Data Index: 723753 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3474. Min Act: -0.1700
Data Index: 3529521 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3407. Min Act: -0.1698
Data Index: 6964242 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3407. Min Act: -0.1700
Data Index: 4135334 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3407. Min Act: -0.1700
Data Index: 6964237 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3339. Min Act: -0.1700
Data Index: 4735054 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3339. Min Act: -0.1700
Data Index: 5173334 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3339. Min Act: -0.1700
Data Index: 6369983 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3273. Min Act: -0.1700
Data Index: 6918018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3206. Min Act: -0.1700
Data Index: 4735033 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3206. Min Act: -0.1700
Data Index: 7553174 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3140. Min Act: -0.1700
Data Index: 6963047 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3140. Min Act: -0.1700
Data Index: 1161481 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3140. Min Act: -0.1700
Data Index: 7701412 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3074. Min Act: -0.1700
Data Index: 1284005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4533. Min Range: -0.4533
Max Act: 0.3074. Min Act: -0.1700
Data Index: 5173330 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19