Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.9297. Min Act: -0.1700
Data Index: 195317 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.8672. Min Act: -0.1700
Data Index: 5722930 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.8672. Min Act: -0.1700
Data Index: 4937625 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.8672. Min Act: -0.1700
Data Index: 4456768 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.8359. Min Act: -0.1700
Data Index: 2839214 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.8359. Min Act: -0.1700
Data Index: 3859477 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.8047. Min Act: -0.1700
Data Index: 7602754 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7734. Min Act: -0.1700
Data Index: 4100103 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7422. Min Act: -0.1700
Data Index: 1733044 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7734. Min Act: -0.1700
Data Index: 467961 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7422. Min Act: -0.1700
Data Index: 2071145 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7422. Min Act: -0.1700
Data Index: 1528468 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7734. Min Act: -0.1700
Data Index: 1176499 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7422. Min Act: -0.1700
Data Index: 4823596 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7734. Min Act: -0.1700
Data Index: 8135400 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7734. Min Act: -0.1700
Data Index: 2939675 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7109. Min Act: -0.1700
Data Index: 4300453 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7109. Min Act: -0.1700
Data Index: 1942045 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7109. Min Act: -0.1700
Data Index: 4813868 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9297. Min Range: -5.9297
Max Act: 5.7422. Min Act: -0.1700
Data Index: 3825845 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19