Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.5857. Min Act: -0.1700
Data Index: 3515029 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.5232. Min Act: -0.1700
Data Index: 4061376 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.4295. Min Act: -0.1700
Data Index: 8407617 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.3357. Min Act: -0.1700
Data Index: 3701296 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.3357. Min Act: -0.1700
Data Index: 7073950 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.3045. Min Act: -0.1700
Data Index: 8372378 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.3045. Min Act: -0.1700
Data Index: 3873182 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.3045. Min Act: -0.1700
Data Index: 1453587 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.2732. Min Act: -0.1700
Data Index: 839785 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.2732. Min Act: -0.1700
Data Index: 4324236 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.2732. Min Act: -0.1700
Data Index: 3821292 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.2107. Min Act: -0.1700
Data Index: 4683427 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.2107. Min Act: -0.1700
Data Index: 748732 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.2107. Min Act: -0.1700
Data Index: 4795716 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.1795. Min Act: -0.1700
Data Index: 7530832 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.1795. Min Act: -0.1700
Data Index: 7632414 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.1482. Min Act: -0.1700
Data Index: 285785 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.1482. Min Act: -0.1700
Data Index: 6819640 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.1482. Min Act: -0.1700
Data Index: 7632028 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5857. Min Range: -5.5857
Max Act: 5.1170. Min Act: -0.1700
Data Index: 809016 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19