Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4968 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.6986. Min Act: -0.1700
Data Index: 3768625 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.3236. Min Act: -0.1700
Data Index: 2545071 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.2924. Min Act: -0.1700
Data Index: 8396853 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.2924. Min Act: -0.1700
Data Index: 8713344 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.1361. Min Act: -0.1700
Data Index: 5581611 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.1361. Min Act: -0.1700
Data Index: 2483885 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.1049. Min Act: -0.1700
Data Index: 2085800 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.0424. Min Act: -0.1700
Data Index: 8531545 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.0424. Min Act: -0.1700
Data Index: 8802624 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.0424. Min Act: -0.1700
Data Index: 354060 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.0424. Min Act: -0.1700
Data Index: 3774304 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.0424. Min Act: -0.1700
Data Index: 4749996 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6986. Min Range: -8.6986
Max Act: 7.9799. Min Act: -0.1700
Data Index: 7915036 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6986. Min Range: -8.6986
Max Act: 8.0424. Min Act: -0.1700
Data Index: 2205074 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6986. Min Range: -8.6986
Max Act: 7.9799. Min Act: -0.1700
Data Index: 4350814 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6986. Min Range: -8.6986
Max Act: 7.9799. Min Act: -0.1700
Data Index: 4703632 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6986. Min Range: -8.6986
Max Act: 7.9799. Min Act: -0.1700
Data Index: 3581678 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6986. Min Range: -8.6986
Max Act: 7.9486. Min Act: -0.1700
Data Index: 549628 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6986. Min Range: -8.6986
Max Act: 7.9486. Min Act: -0.1700
Data Index: 532744 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6986. Min Range: -8.6986
Max Act: 7.9486. Min Act: -0.1700
Data Index: 5837339 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19