Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.5067. Min Act: -0.1700
Data Index: 8432987 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.4442. Min Act: -0.1700
Data Index: 3454255 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.4442. Min Act: -0.1700
Data Index: 6325731 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.4755. Min Act: -0.1700
Data Index: 4674461 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.4755. Min Act: -0.1700
Data Index: 5381896 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.3505. Min Act: -0.1700
Data Index: 8013835 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.3817. Min Act: -0.1700
Data Index: 4623475 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.4130. Min Act: -0.1700
Data Index: 140550 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.4130. Min Act: -0.1700
Data Index: 2652224 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.3505. Min Act: -0.1700
Data Index: 7567069 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.3505. Min Act: -0.1700
Data Index: 8522776 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.3192. Min Act: -0.1700
Data Index: 7077231 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.3505. Min Act: -0.1700
Data Index: 485308 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.3192. Min Act: -0.1700
Data Index: 1504894 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.3505. Min Act: -0.1700
Data Index: 7808064 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.3505. Min Act: -0.1700
Data Index: 1386116 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.3505. Min Act: -0.1700
Data Index: 7238675 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.2880. Min Act: -0.1700
Data Index: 2507057 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.3192. Min Act: -0.1700
Data Index: 4517862 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5067. Min Range: -5.5067
Max Act: 5.3192. Min Act: -0.1700
Data Index: 5396104 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19