Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6326 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0571. Min Range: -8.0571
Max Act: 8.0571. Min Act: -0.1700
Data Index: 4636353 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.4946. Min Act: -0.1700
Data Index: 2795724 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.4009. Min Act: -0.1700
Data Index: 8723795 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.4009. Min Act: -0.1700
Data Index: 970138 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.3696. Min Act: -0.1700
Data Index: 5816129 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.3696. Min Act: -0.1700
Data Index: 7263446 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.3696. Min Act: -0.1700
Data Index: 7579384 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.3384. Min Act: -0.1700
Data Index: 5520873 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.3071. Min Act: -0.1700
Data Index: 2746044 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.3384. Min Act: -0.1700
Data Index: 5199 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.2759. Min Act: -0.1700
Data Index: 4048609 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.2446. Min Act: -0.1700
Data Index: 8568515 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.2446. Min Act: -0.1700
Data Index: 776270 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.1821. Min Act: -0.1700
Data Index: 4623032 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.1821. Min Act: -0.1700
Data Index: 410306 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.1509. Min Act: -0.1700
Data Index: 4697154 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.1821. Min Act: -0.1700
Data Index: 3344466 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.1196. Min Act: -0.1700
Data Index: 1185636 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.1509. Min Act: -0.1700
Data Index: 3221334 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0571. Min Range: -8.0571
Max Act: 7.1509. Min Act: -0.1700
Data Index: 5235235 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19