Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3444. Min Range: -8.3444
Max Act: 8.3444. Min Act: -0.1700
Data Index: 5682621 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3444. Min Range: -8.3444
Max Act: 8.0319. Min Act: -0.1700
Data Index: 5353398 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3444. Min Range: -8.3444
Max Act: 8.0944. Min Act: -0.1700
Data Index: 1786910 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.8756. Min Act: -0.1700
Data Index: 1687887 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.9381. Min Act: -0.1700
Data Index: 7200506 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.8756. Min Act: -0.1700
Data Index: 8207505 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.9069. Min Act: -0.1700
Data Index: 4860626 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.8444. Min Act: -0.1700
Data Index: 5101384 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.8131. Min Act: -0.1700
Data Index: 608475 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.8444. Min Act: -0.1700
Data Index: 4772495 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.6881. Min Act: -0.1700
Data Index: 3777744 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.6881. Min Act: -0.1700
Data Index: 6014688 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.6881. Min Act: -0.1700
Data Index: 358475 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.6256. Min Act: -0.1700
Data Index: 4810372 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.5631. Min Act: -0.1700
Data Index: 7453168 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.5631. Min Act: -0.1700
Data Index: 1972576 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.4069. Min Act: -0.1700
Data Index: 5995595 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.4694. Min Act: -0.1700
Data Index: 3268141 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.5006. Min Act: -0.1700
Data Index: 4623380 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3444. Min Range: -8.3444
Max Act: 7.4381. Min Act: -0.1700
Data Index: 2986694 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19