Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4177 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.7844. Min Act: -0.1700
Data Index: 2385382 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.8004. Min Act: -0.1700
Data Index: 1405235 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.7366. Min Act: -0.1700
Data Index: 135673 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.7206. Min Act: -0.1700
Data Index: 4747165 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.7046. Min Act: -0.1700
Data Index: 1862658 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.6726. Min Act: -0.1700
Data Index: 8158015 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.6726. Min Act: -0.1700
Data Index: 8379886 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.6405. Min Act: -0.1700
Data Index: 1428532 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.6244. Min Act: -0.1700
Data Index: 4880417 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.6405. Min Act: -0.1700
Data Index: 5264389 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.6084. Min Act: -0.1700
Data Index: 7185946 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.6084. Min Act: -0.1700
Data Index: 4427031 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.5923. Min Act: -0.1700
Data Index: 867150 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.5277. Min Act: -0.1700
Data Index: 8607649 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.5277. Min Act: -0.1700
Data Index: 7793713 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.5277. Min Act: -0.1700
Data Index: 4569943 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.5115. Min Act: -0.1700
Data Index: 6735973 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.4953. Min Act: -0.1700
Data Index: 6268852 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.5115. Min Act: -0.1700
Data Index: 633939 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8004. Min Range: -2.8004
Max Act: 2.5115. Min Act: -0.1700
Data Index: 2816898 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19