Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 498 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.4930. Min Act: -0.1700
Data Index: 7141411 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.4930. Min Act: -0.1700
Data Index: 3922760 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.1493. Min Act: -0.1699
Data Index: 7550078 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.1180. Min Act: -0.1699
Data Index: 5880570 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.1493. Min Act: -0.1700
Data Index: 6966670 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.1493. Min Act: -0.1700
Data Index: 3639445 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.0868. Min Act: -0.1700
Data Index: 4531327 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.0555. Min Act: -0.1700
Data Index: 2993993 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.0555. Min Act: -0.1700
Data Index: 4896155 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.0555. Min Act: -0.1700
Data Index: 7782340 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4930. Min Range: -5.4930
Max Act: 4.9930. Min Act: -0.1700
Data Index: 7678067 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4930. Min Range: -5.4930
Max Act: 4.9930. Min Act: -0.1700
Data Index: 7383975 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.0243. Min Act: -0.1700
Data Index: 3164431 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.0868. Min Act: -0.1700
Data Index: 1800447 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.0868. Min Act: -0.1700
Data Index: 2295136 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4930. Min Range: -5.4930
Max Act: 4.9930. Min Act: -0.1700
Data Index: 3056916 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4930. Min Range: -5.4930
Max Act: 5.0243. Min Act: -0.1700
Data Index: 3533030 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4930. Min Range: -5.4930
Max Act: 4.9305. Min Act: -0.1700
Data Index: 729357 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4930. Min Range: -5.4930
Max Act: 4.8993. Min Act: -0.1700
Data Index: 956528 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4930. Min Range: -5.4930
Max Act: 4.9618. Min Act: -0.1699
Data Index: 140192 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19