Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4803 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1253. Min Range: -5.1253
Max Act: 5.1253. Min Act: -0.1700
Data Index: 1587453 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1253. Min Range: -5.1253
Max Act: 5.0003. Min Act: -0.1700
Data Index: 3072036 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1253. Min Range: -5.1253
Max Act: 5.0003. Min Act: -0.1700
Data Index: 5048913 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9690. Min Act: -0.1700
Data Index: 8752198 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9378. Min Act: -0.1700
Data Index: 7866344 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9690. Min Act: -0.1700
Data Index: 5225247 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9690. Min Act: -0.1700
Data Index: 72719 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9378. Min Act: -0.1700
Data Index: 1148628 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9065. Min Act: -0.1700
Data Index: 5281130 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9065. Min Act: -0.1700
Data Index: 1563566 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9065. Min Act: -0.1700
Data Index: 2178136 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9065. Min Act: -0.1700
Data Index: 6667043 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9065. Min Act: -0.1700
Data Index: 6992002 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9065. Min Act: -0.1700
Data Index: 1519399 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9065. Min Act: -0.1700
Data Index: 737488 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9378. Min Act: -0.1700
Data Index: 7267712 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9065. Min Act: -0.1700
Data Index: 6235120 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9065. Min Act: -0.1700
Data Index: 2937504 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9065. Min Act: -0.1700
Data Index: 7365029 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9065. Min Act: -0.1700
Data Index: 4890332 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19