Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2810 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2717. Min Range: -5.2717
Max Act: 5.2717. Min Act: -0.1700
Data Index: 3011303 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2717. Min Range: -5.2717
Max Act: 5.2092. Min Act: -0.1700
Data Index: 8435242 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2717. Min Range: -5.2717
Max Act: 5.1467. Min Act: -0.1700
Data Index: 6176339 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2717. Min Range: -5.2717
Max Act: 5.0217. Min Act: -0.1700
Data Index: 8379652 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2717. Min Range: -5.2717
Max Act: 5.0217. Min Act: -0.1700
Data Index: 291691 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2717. Min Range: -5.2717
Max Act: 5.0217. Min Act: -0.1700
Data Index: 4871657 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9904. Min Act: -0.1700
Data Index: 7145897 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9592. Min Act: -0.1700
Data Index: 394645 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9592. Min Act: -0.1700
Data Index: 5181121 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9279. Min Act: -0.1700
Data Index: 1815864 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9279. Min Act: -0.1700
Data Index: 597000 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9279. Min Act: -0.1700
Data Index: 8510552 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9592. Min Act: -0.1700
Data Index: 3921310 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.8967. Min Act: -0.1700
Data Index: 6588923 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.8967. Min Act: -0.1700
Data Index: 1208569 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9279. Min Act: -0.1700
Data Index: 3592168 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.8967. Min Act: -0.1700
Data Index: 888818 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.9279. Min Act: -0.1700
Data Index: 5472058 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.8967. Min Act: -0.1700
Data Index: 7421655 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2717. Min Range: -5.2717
Max Act: 4.8967. Min Act: -0.1700
Data Index: 7830720 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19