Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6393. Min Range: -8.6393
Max Act: 8.6393. Min Act: -0.1700
Data Index: 2027478 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6393. Min Range: -8.6393
Max Act: 8.4518. Min Act: -0.1700
Data Index: 3527597 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6393. Min Range: -8.6393
Max Act: 8.2643. Min Act: -0.1700
Data Index: 4709895 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6393. Min Range: -8.6393
Max Act: 8.1393. Min Act: -0.1700
Data Index: 3074966 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6393. Min Range: -8.6393
Max Act: 8.1393. Min Act: -0.1700
Data Index: 4810608 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6393. Min Range: -8.6393
Max Act: 8.1393. Min Act: -0.1700
Data Index: 4235740 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6393. Min Range: -8.6393
Max Act: 8.0768. Min Act: -0.1700
Data Index: 988604 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6393. Min Range: -8.6393
Max Act: 8.0768. Min Act: -0.1700
Data Index: 6195530 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6393. Min Range: -8.6393
Max Act: 8.0768. Min Act: -0.1700
Data Index: 5401156 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6393. Min Range: -8.6393
Max Act: 7.9518. Min Act: -0.1700
Data Index: 8001288 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6393. Min Range: -8.6393
Max Act: 7.8893. Min Act: -0.1700
Data Index: 2670625 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6393. Min Range: -8.6393
Max Act: 7.9518. Min Act: -0.1700
Data Index: 6991589 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6393. Min Range: -8.6393
Max Act: 7.9518. Min Act: -0.1700
Data Index: 6587889 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6393. Min Range: -8.6393
Max Act: 7.9518. Min Act: -0.1700
Data Index: 6459038 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6393. Min Range: -8.6393
Max Act: 7.9518. Min Act: -0.1700
Data Index: 5693676 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6393. Min Range: -8.6393
Max Act: 7.8893. Min Act: -0.1700
Data Index: 621266 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6393. Min Range: -8.6393
Max Act: 7.8893. Min Act: -0.1700
Data Index: 452030 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6393. Min Range: -8.6393
Max Act: 7.8268. Min Act: -0.1700
Data Index: 3527590 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6393. Min Range: -8.6393
Max Act: 7.8268. Min Act: -0.1700
Data Index: 4754231 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6393. Min Range: -8.6393
Max Act: 7.8268. Min Act: -0.1700
Data Index: 3413627 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19