Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3782 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.4390. Min Act: -0.1700
Data Index: 8827197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.4390. Min Act: -0.1700
Data Index: 2570620 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.3140. Min Act: -0.1700
Data Index: 1707283 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.3140. Min Act: -0.1700
Data Index: 8001576 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.3140. Min Act: -0.1700
Data Index: 6519395 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.2514. Min Act: -0.1700
Data Index: 2082202 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.2514. Min Act: -0.1700
Data Index: 1604390 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.2202. Min Act: -0.1700
Data Index: 6636582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.2202. Min Act: -0.1700
Data Index: 8186723 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.2202. Min Act: -0.1700
Data Index: 8746456 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.1889. Min Act: -0.1700
Data Index: 1228922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.1889. Min Act: -0.1700
Data Index: 7258490 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.1889. Min Act: -0.1700
Data Index: 5761814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.1889. Min Act: -0.1700
Data Index: 514761 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.1889. Min Act: -0.1700
Data Index: 4942645 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.1889. Min Act: -0.1699
Data Index: 3313133 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.1889. Min Act: -0.1700
Data Index: 697300 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.1577. Min Act: -0.1700
Data Index: 2992513 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.1577. Min Act: -0.1700
Data Index: 2577059 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4390. Min Range: -4.4390
Max Act: 4.1577. Min Act: -0.1700
Data Index: 2717386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19