Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1700 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3639. Min Range: -6.3639
Max Act: 6.3639. Min Act: -0.1700
Data Index: 5232476 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3639. Min Range: -6.3639
Max Act: 6.2389. Min Act: -0.1700
Data Index: 5324936 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3639. Min Range: -6.3639
Max Act: 6.1451. Min Act: -0.1700
Data Index: 4278893 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.9576. Min Act: -0.1700
Data Index: 3266884 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.9576. Min Act: -0.1700
Data Index: 3476118 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.8639. Min Act: -0.1700
Data Index: 6579035 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.8326. Min Act: -0.1700
Data Index: 4385361 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.8326. Min Act: -0.1700
Data Index: 4385366 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.8014. Min Act: -0.1700
Data Index: 3471080 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.8014. Min Act: -0.1700
Data Index: 5412214 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.7389. Min Act: -0.1700
Data Index: 3522077 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.7389. Min Act: -0.1700
Data Index: 2380022 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.6764. Min Act: -0.1700
Data Index: 2136341 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.6139. Min Act: -0.1700
Data Index: 2708281 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.6451. Min Act: -0.1700
Data Index: 2964011 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.6139. Min Act: -0.1700
Data Index: 8636158 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.6139. Min Act: -0.1700
Data Index: 8579 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.5826. Min Act: -0.1700
Data Index: 1691100 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.5514. Min Act: -0.1700
Data Index: 1378295 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3639. Min Range: -6.3639
Max Act: 5.5514. Min Act: -0.1700
Data Index: 1678506 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19