Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.9075. Min Act: -0.1700
Data Index: 920017 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.9075. Min Act: -0.1700
Data Index: 64148 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.8450. Min Act: -0.1700
Data Index: 2666090 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.7825. Min Act: -0.1700
Data Index: 4252397 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.7825. Min Act: -0.1700
Data Index: 3764170 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.7200. Min Act: -0.1700
Data Index: 3753723 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.6575. Min Act: -0.1700
Data Index: 1289521 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.5950. Min Act: -0.1700
Data Index: 5952963 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.5950. Min Act: -0.1700
Data Index: 5982232 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.5325. Min Act: -0.1700
Data Index: 2732068 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.5325. Min Act: -0.1700
Data Index: 920016 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.4700. Min Act: -0.1700
Data Index: 2888135 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.4700. Min Act: -0.1700
Data Index: 2518325 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.3450. Min Act: -0.1700
Data Index: 1593726 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.3450. Min Act: -0.1700
Data Index: 168657 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.3450. Min Act: -0.1700
Data Index: 817263 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.3450. Min Act: -0.1700
Data Index: 8395869 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.2825. Min Act: -0.1700
Data Index: 5506065 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.3450. Min Act: -0.1700
Data Index: 4771660 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9075. Min Range: -10.9075
Max Act: 10.2825. Min Act: -0.1700
Data Index: 3413667 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19