Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5500. Min Range: -7.5500
Max Act: 7.5500. Min Act: -0.1700
Data Index: 4091196 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5500. Min Range: -7.5500
Max Act: 7.2688. Min Act: -0.1700
Data Index: 6206503 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5500. Min Range: -7.5500
Max Act: 7.1750. Min Act: -0.1700
Data Index: 6995898 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5500. Min Range: -7.5500
Max Act: 7.1125. Min Act: -0.1700
Data Index: 3523115 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5500. Min Range: -7.5500
Max Act: 7.1125. Min Act: -0.1700
Data Index: 4382102 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5500. Min Range: -7.5500
Max Act: 7.0813. Min Act: -0.1700
Data Index: 4493864 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5500. Min Range: -7.5500
Max Act: 7.0188. Min Act: -0.1700
Data Index: 304285 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5500. Min Range: -7.5500
Max Act: 7.0188. Min Act: -0.1700
Data Index: 2776641 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5500. Min Range: -7.5500
Max Act: 7.0188. Min Act: -0.1700
Data Index: 5917105 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5500. Min Range: -7.5500
Max Act: 7.0188. Min Act: -0.1700
Data Index: 6982036 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5500. Min Range: -7.5500
Max Act: 6.9875. Min Act: -0.1700
Data Index: 1864806 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5500. Min Range: -7.5500
Max Act: 6.9563. Min Act: -0.1700
Data Index: 626449 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5500. Min Range: -7.5500
Max Act: 6.9563. Min Act: -0.1700
Data Index: 8202144 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5500. Min Range: -7.5500
Max Act: 6.9563. Min Act: -0.1700
Data Index: 6916747 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5500. Min Range: -7.5500
Max Act: 6.9563. Min Act: -0.1700
Data Index: 4939719 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5500. Min Range: -7.5500
Max Act: 6.9875. Min Act: -0.1700
Data Index: 2763604 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5500. Min Range: -7.5500
Max Act: 6.9563. Min Act: -0.1700
Data Index: 6587130 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5500. Min Range: -7.5500
Max Act: 6.9250. Min Act: -0.1700
Data Index: 3195257 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5500. Min Range: -7.5500
Max Act: 6.8938. Min Act: -0.1700
Data Index: 973244 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5500. Min Range: -7.5500
Max Act: 6.9250. Min Act: -0.1700
Data Index: 2329533 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19