Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2662. Min Range: -6.2662
Max Act: 6.2662. Min Act: -0.1700
Data Index: 1389432 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2662. Min Range: -6.2662
Max Act: 6.1100. Min Act: -0.1700
Data Index: 86811 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2662. Min Range: -6.2662
Max Act: 6.0787. Min Act: -0.1700
Data Index: 7102775 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2662. Min Range: -6.2662
Max Act: 6.0162. Min Act: -0.1700
Data Index: 429351 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.9225. Min Act: -0.1700
Data Index: 4340880 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.9225. Min Act: -0.1700
Data Index: 8436363 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.8912. Min Act: -0.1700
Data Index: 1159078 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.8600. Min Act: -0.1700
Data Index: 4340875 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.8600. Min Act: -0.1700
Data Index: 5543521 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.8287. Min Act: -0.1700
Data Index: 1505775 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.8287. Min Act: -0.1700
Data Index: 1742600 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.8287. Min Act: -0.1700
Data Index: 46899 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.8287. Min Act: -0.1700
Data Index: 7038076 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.7975. Min Act: -0.1700
Data Index: 7264370 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.7975. Min Act: -0.1700
Data Index: 1200333 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.7662. Min Act: -0.1700
Data Index: 5655885 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.7350. Min Act: -0.1700
Data Index: 583303 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.7037. Min Act: -0.1700
Data Index: 3881537 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.6412. Min Act: -0.1700
Data Index: 3990474 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2662. Min Range: -6.2662
Max Act: 5.6725. Min Act: -0.1700
Data Index: 4443882 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19