Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 143 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3499. Min Range: -8.3499
Max Act: 8.3499. Min Act: -0.1700
Data Index: 8119594 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3499. Min Range: -8.3499
Max Act: 8.2874. Min Act: -0.1700
Data Index: 2250538 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3499. Min Range: -8.3499
Max Act: 8.1624. Min Act: -0.1700
Data Index: 5132547 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3499. Min Range: -8.3499
Max Act: 8.0999. Min Act: -0.1700
Data Index: 565522 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3499. Min Range: -8.3499
Max Act: 8.0374. Min Act: -0.1700
Data Index: 2959590 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3499. Min Range: -8.3499
Max Act: 8.0374. Min Act: -0.1700
Data Index: 1349949 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3499. Min Range: -8.3499
Max Act: 8.0374. Min Act: -0.1700
Data Index: 7317790 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.9749. Min Act: -0.1700
Data Index: 1264034 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.9124. Min Act: -0.1700
Data Index: 8017192 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.9124. Min Act: -0.1700
Data Index: 4881248 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.8499. Min Act: -0.1700
Data Index: 4419122 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.8499. Min Act: -0.1700
Data Index: 7387613 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.8499. Min Act: -0.1700
Data Index: 2412642 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.8499. Min Act: -0.1700
Data Index: 6170026 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.8499. Min Act: -0.1700
Data Index: 494598 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.8499. Min Act: -0.1700
Data Index: 5926550 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.7874. Min Act: -0.1700
Data Index: 2364152 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.7874. Min Act: -0.1700
Data Index: 2254935 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.7874. Min Act: -0.1700
Data Index: 1625104 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3499. Min Range: -8.3499
Max Act: 7.7874. Min Act: -0.1700
Data Index: 930870 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19