Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.6301. Min Act: -0.1700
Data Index: 6457684 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.6301. Min Act: -0.1700
Data Index: 2403487 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5988. Min Act: -0.1700
Data Index: 2120120 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5988. Min Act: -0.1700
Data Index: 95990 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5988. Min Act: -0.1700
Data Index: 1221543 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5676. Min Act: -0.1700
Data Index: 4766265 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5676. Min Act: -0.1700
Data Index: 2011487 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5676. Min Act: -0.1700
Data Index: 4433733 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5363. Min Act: -0.1699
Data Index: 7954630 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5676. Min Act: -0.1700
Data Index: 3164383 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5363. Min Act: -0.1700
Data Index: 4770853 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5676. Min Act: -0.1700
Data Index: 335546 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5363. Min Act: -0.1700
Data Index: 4038929 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5363. Min Act: -0.1700
Data Index: 1639022 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5363. Min Act: -0.1700
Data Index: 2562632 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5363. Min Act: -0.1700
Data Index: 4542413 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5363. Min Act: -0.1700
Data Index: 5835878 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5051. Min Act: -0.1700
Data Index: 6198527 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.4738. Min Act: -0.1700
Data Index: 2230314 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6301. Min Range: -5.6301
Max Act: 5.5363. Min Act: -0.1700
Data Index: 6319878 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19