Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2160 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0590. Min Range: -4.0590
Max Act: 4.0590. Min Act: -0.1700
Data Index: 4016366 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.9965. Min Act: -0.1700
Data Index: 3453243 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0590. Min Range: -4.0590
Max Act: 4.0590. Min Act: -0.1700
Data Index: 617456 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.9652. Min Act: -0.1700
Data Index: 3568403 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0590. Min Range: -4.0590
Max Act: 4.0277. Min Act: -0.1700
Data Index: 5551183 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.9340. Min Act: -0.1700
Data Index: 6775777 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.9027. Min Act: -0.1700
Data Index: 3070372 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8871. Min Act: -0.1700
Data Index: 1304622 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8714. Min Act: -0.1700
Data Index: 836053 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8714. Min Act: -0.1700
Data Index: 2764275 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8402. Min Act: -0.1700
Data Index: 4954590 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8714. Min Act: -0.1700
Data Index: 6723216 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8402. Min Act: -0.1700
Data Index: 5019640 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8089. Min Act: -0.1700
Data Index: 8140400 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8089. Min Act: -0.1700
Data Index: 4908825 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.8245. Min Act: -0.1700
Data Index: 6500023 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.7933. Min Act: -0.1700
Data Index: 1462107 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.7776. Min Act: -0.1700
Data Index: 8489943 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.7776. Min Act: -0.1700
Data Index: 2122723 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0590. Min Range: -4.0590
Max Act: 3.7776. Min Act: -0.1700
Data Index: 6176807 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19