Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2913 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3477. Min Range: -4.3477
Max Act: 4.3477. Min Act: -0.1700
Data Index: 8448055 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3477. Min Range: -4.3477
Max Act: 4.0351. Min Act: -0.1700
Data Index: 4444628 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3477. Min Range: -4.3477
Max Act: 4.0039. Min Act: -0.1700
Data Index: 198341 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.9413. Min Act: -0.1700
Data Index: 2648840 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.9101. Min Act: -0.1700
Data Index: 7219270 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.9101. Min Act: -0.1700
Data Index: 4166640 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.8788. Min Act: -0.1700
Data Index: 4444618 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.8788. Min Act: -0.1700
Data Index: 5154193 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.8475. Min Act: -0.1700
Data Index: 5481161 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.8163. Min Act: -0.1700
Data Index: 4365206 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.8163. Min Act: -0.1700
Data Index: 5181656 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.8475. Min Act: -0.1700
Data Index: 5606767 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.8163. Min Act: -0.1700
Data Index: 3709530 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.8475. Min Act: -0.1700
Data Index: 2423444 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.8006. Min Act: -0.1700
Data Index: 2578421 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.7850. Min Act: -0.1700
Data Index: 8797542 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.8006. Min Act: -0.1700
Data Index: 8828018 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.8163. Min Act: -0.1700
Data Index: 3163727 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.7693. Min Act: -0.1700
Data Index: 923668 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3477. Min Range: -4.3477
Max Act: 3.8006. Min Act: -0.1700
Data Index: 1547452 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19