Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3015 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1656. Min Range: -5.1656
Max Act: 5.1656. Min Act: -0.1700
Data Index: 655337 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1656. Min Range: -5.1656
Max Act: 5.1344. Min Act: -0.1700
Data Index: 5272777 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1656. Min Range: -5.1656
Max Act: 5.0719. Min Act: -0.1700
Data Index: 7033916 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.9781. Min Act: -0.1700
Data Index: 6541957 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.9781. Min Act: -0.1700
Data Index: 3049225 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.9469. Min Act: -0.1700
Data Index: 5471580 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.9156. Min Act: -0.1700
Data Index: 1989880 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.9156. Min Act: -0.1700
Data Index: 4606690 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.8844. Min Act: -0.1700
Data Index: 1348880 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.8844. Min Act: -0.1700
Data Index: 4684592 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.8844. Min Act: -0.1700
Data Index: 7327393 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.8844. Min Act: -0.1700
Data Index: 737302 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.8844. Min Act: -0.1700
Data Index: 1349899 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.8219. Min Act: -0.1700
Data Index: 4958950 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.7906. Min Act: -0.1700
Data Index: 3227493 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.8219. Min Act: -0.1700
Data Index: 3058868 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.8219. Min Act: -0.1700
Data Index: 5833997 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.8219. Min Act: -0.1700
Data Index: 5480991 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.7906. Min Act: -0.1700
Data Index: 1323692 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1656. Min Range: -5.1656
Max Act: 4.7906. Min Act: -0.1700
Data Index: 2928200 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19