Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1746 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.4418. Min Act: -0.1700
Data Index: 3748484 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.3438. Min Act: -0.1700
Data Index: 5888630 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.3110. Min Act: -0.1700
Data Index: 3762790 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.3110. Min Act: -0.1700
Data Index: 7777523 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2781. Min Act: -0.1700
Data Index: 454739 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2616. Min Act: -0.1700
Data Index: 1491161 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2616. Min Act: -0.1700
Data Index: 8398397 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2616. Min Act: -0.1700
Data Index: 8339017 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2451. Min Act: -0.1700
Data Index: 5883477 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2451. Min Act: -0.1700
Data Index: 8438515 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2451. Min Act: -0.1700
Data Index: 365670 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2120. Min Act: -0.1700
Data Index: 3311280 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2285. Min Act: -0.1700
Data Index: 362959 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2451. Min Act: -0.1700
Data Index: 1274927 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2285. Min Act: -0.1700
Data Index: 3940259 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2285. Min Act: -0.1700
Data Index: 1174260 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2285. Min Act: -0.1700
Data Index: 7527894 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2285. Min Act: -0.1700
Data Index: 3545788 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2451. Min Act: -0.1700
Data Index: 2259285 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4418. Min Range: -2.4418
Max Act: 2.2285. Min Act: -0.1700
Data Index: 2090153 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19