Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3735 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.7405. Min Act: -0.1700
Data Index: 6645838 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.7405. Min Act: -0.1700
Data Index: 5825955 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.7405. Min Act: -0.1685
Data Index: 2631315 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.7405. Min Act: -0.1700
Data Index: 5075978 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.7405. Min Act: -0.1700
Data Index: 3405291 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1700
Data Index: 5362886 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1700
Data Index: 2062288 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1700
Data Index: 1961940 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1700
Data Index: 2493374 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1700
Data Index: 2772780 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1697
Data Index: 5009834 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1700
Data Index: 4747367 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1699
Data Index: 1766612 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1633
Data Index: 3656211 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1540
Data Index: 3656208 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1697
Data Index: 2664843 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1700
Data Index: 958628 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1700
Data Index: 141455 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1700
Data Index: 777653 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7405. Min Range: -2.7405
Max Act: 2.6925. Min Act: -0.1687
Data Index: 2602760 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19