Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 646 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.9545. Min Act: -0.1700
Data Index: 4171430 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.9545. Min Act: -0.1700
Data Index: 5634351 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.6732. Min Act: -0.1700
Data Index: 3577176 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.6420. Min Act: -0.1700
Data Index: 7674950 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.6420. Min Act: -0.1700
Data Index: 7222405 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.6107. Min Act: -0.1700
Data Index: 8259293 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.6420. Min Act: -0.1700
Data Index: 8141263 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.6107. Min Act: -0.1700
Data Index: 1082137 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.6107. Min Act: -0.1700
Data Index: 5404281 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.6107. Min Act: -0.1700
Data Index: 7967749 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.5482. Min Act: -0.1700
Data Index: 8593728 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.5170. Min Act: -0.1700
Data Index: 5044209 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.4857. Min Act: -0.1700
Data Index: 8317271 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.5170. Min Act: -0.1700
Data Index: 2619691 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.4857. Min Act: -0.1700
Data Index: 7364530 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.5170. Min Act: -0.1700
Data Index: 8706071 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.4232. Min Act: -0.1700
Data Index: 6975219 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.4857. Min Act: -0.1700
Data Index: 591700 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.4545. Min Act: -0.1700
Data Index: 2546130 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9545. Min Range: -5.9545
Max Act: 5.4545. Min Act: -0.1700
Data Index: 5971559 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19