Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.5351. Min Act: -0.1700
Data Index: 4247486 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.5351. Min Act: -0.1700
Data Index: 4247484 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.2538. Min Act: -0.1700
Data Index: 5873756 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.1601. Min Act: -0.1700
Data Index: 1642173 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.1288. Min Act: -0.1700
Data Index: 7446388 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.1288. Min Act: -0.1700
Data Index: 4868283 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0976. Min Act: -0.1700
Data Index: 2685781 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0976. Min Act: -0.1700
Data Index: 8105346 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0976. Min Act: -0.1700
Data Index: 4498595 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0976. Min Act: -0.1700
Data Index: 3230891 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0976. Min Act: -0.1700
Data Index: 7023128 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0663. Min Act: -0.1700
Data Index: 8601635 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0663. Min Act: -0.1700
Data Index: 5953376 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0350. Min Act: -0.1700
Data Index: 4868284 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0350. Min Act: -0.1700
Data Index: 30551 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0350. Min Act: -0.1700
Data Index: 3926556 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0350. Min Act: -0.1700
Data Index: 3824666 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0350. Min Act: -0.1700
Data Index: 2676703 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0350. Min Act: -0.1700
Data Index: 5841314 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5351. Min Range: -4.5351
Max Act: 4.0350. Min Act: -0.1700
Data Index: 5742772 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19