Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1513 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1293. Min Range: -6.1293
Max Act: 6.1293. Min Act: -0.1700
Data Index: 3401124 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1293. Min Range: -6.1293
Max Act: 6.0668. Min Act: -0.1700
Data Index: 3137876 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1293. Min Range: -6.1293
Max Act: 6.0980. Min Act: -0.1700
Data Index: 7830409 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1293. Min Range: -6.1293
Max Act: 6.0355. Min Act: -0.1700
Data Index: 883909 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.9105. Min Act: -0.1700
Data Index: 1609303 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.9105. Min Act: -0.1700
Data Index: 3021786 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.8480. Min Act: -0.1700
Data Index: 7777063 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.8168. Min Act: -0.1700
Data Index: 2386180 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.7855. Min Act: -0.1700
Data Index: 4154745 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.7855. Min Act: -0.1700
Data Index: 1813851 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.7855. Min Act: -0.1700
Data Index: 8540674 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.7855. Min Act: -0.1700
Data Index: 7135569 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.7230. Min Act: -0.1700
Data Index: 6100162 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.7543. Min Act: -0.1700
Data Index: 2417775 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.7543. Min Act: -0.1700
Data Index: 7999835 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.6918. Min Act: -0.1700
Data Index: 84049 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.6918. Min Act: -0.1700
Data Index: 8654677 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.6918. Min Act: -0.1700
Data Index: 923247 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.6918. Min Act: -0.1700
Data Index: 2238141 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1293. Min Range: -6.1293
Max Act: 5.6918. Min Act: -0.1700
Data Index: 7252643 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19