Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.2054. Min Act: -0.1700
Data Index: 7760752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.1429. Min Act: -0.1700
Data Index: 1535594 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.1429. Min Act: -0.1700
Data Index: 7036805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.1116. Min Act: -0.1700
Data Index: 5678797 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.1116. Min Act: -0.1700
Data Index: 8573233 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.1116. Min Act: -0.1700
Data Index: 3690328 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.1116. Min Act: -0.1700
Data Index: 7309284 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0804. Min Act: -0.1700
Data Index: 6255359 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0804. Min Act: -0.1700
Data Index: 1398804 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0491. Min Act: -0.1700
Data Index: 1646614 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0491. Min Act: -0.1700
Data Index: 4321345 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0491. Min Act: -0.1700
Data Index: 8102455 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0491. Min Act: -0.1700
Data Index: 1518082 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0491. Min Act: -0.1700
Data Index: 7091589 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0491. Min Act: -0.1700
Data Index: 6525871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0491. Min Act: -0.1700
Data Index: 1317856 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0491. Min Act: -0.1700
Data Index: 6489461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0491. Min Act: -0.1700
Data Index: 1290572 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0179. Min Act: -0.1700
Data Index: 276257 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2054. Min Range: -4.2054
Max Act: 4.0179. Min Act: -0.1700
Data Index: 3127712 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19