Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 141 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.5605. Min Act: -0.1700
Data Index: 4177644 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.2792. Min Act: -0.1700
Data Index: 2983035 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.2167. Min Act: -0.1700
Data Index: 6369797 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.1542. Min Act: -0.1700
Data Index: 4503118 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.1542. Min Act: -0.1700
Data Index: 7180314 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.1542. Min Act: -0.1700
Data Index: 359754 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.1230. Min Act: -0.1700
Data Index: 2169467 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.1230. Min Act: -0.1700
Data Index: 5983239 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.1230. Min Act: -0.1700
Data Index: 5735782 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.0917. Min Act: -0.1700
Data Index: 1658737 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.0917. Min Act: -0.1700
Data Index: 7159068 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.0917. Min Act: -0.1700
Data Index: 6746390 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.0917. Min Act: -0.1700
Data Index: 7894040 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.0605. Min Act: -0.1700
Data Index: 8035203 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.0292. Min Act: -0.1700
Data Index: 8100395 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.0292. Min Act: -0.1700
Data Index: 702751 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.0292. Min Act: -0.1700
Data Index: 5036072 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5605. Min Range: -5.5605
Max Act: 4.9980. Min Act: -0.1700
Data Index: 2409380 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5605. Min Range: -5.5605
Max Act: 5.0292. Min Act: -0.1700
Data Index: 748163 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5605. Min Range: -5.5605
Max Act: 4.9667. Min Act: -0.1700
Data Index: 3850812 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19