Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4124 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.5786. Min Range: -17.5786
Max Act: 17.5786. Min Act: -0.1700
Data Index: 933921 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.5786. Min Range: -17.5786
Max Act: 17.5786. Min Act: -0.1700
Data Index: 6321162 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.5786. Min Range: -17.5786
Max Act: 17.2036. Min Act: -0.1700
Data Index: 4352199 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.5786. Min Range: -17.5786
Max Act: 17.0786. Min Act: -0.1700
Data Index: 7064880 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.5786. Min Range: -17.5786
Max Act: 17.0786. Min Act: -0.1700
Data Index: 7308972 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.9536. Min Act: -0.1700
Data Index: 2598633 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.5786. Min Range: -17.5786
Max Act: 17.0786. Min Act: -0.1700
Data Index: 2751154 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.9536. Min Act: -0.1700
Data Index: 3168833 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.9536. Min Act: -0.1700
Data Index: 6434316 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.8286. Min Act: -0.1700
Data Index: 4832452 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.8286. Min Act: -0.1700
Data Index: 638441 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.8286. Min Act: -0.1700
Data Index: 8745936 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.8286. Min Act: -0.1700
Data Index: 7704748 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.8286. Min Act: -0.1700
Data Index: 3974202 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.8286. Min Act: -0.1700
Data Index: 440475 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.9536. Min Act: -0.1700
Data Index: 1828586 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.8286. Min Act: -0.1700
Data Index: 5716561 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.8286. Min Act: -0.1700
Data Index: 3730384 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.7036. Min Act: -0.1700
Data Index: 1772092 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.5786. Min Range: -17.5786
Max Act: 16.7036. Min Act: -0.1700
Data Index: 5247542 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19