Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 514 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.4232. Min Act: -0.1700
Data Index: 6589849 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.4075. Min Act: -0.1700
Data Index: 5579242 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.4232. Min Act: -0.1700
Data Index: 4791721 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.3605. Min Act: -0.1700
Data Index: 5672975 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.3761. Min Act: -0.1700
Data Index: 8132152 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.3448. Min Act: -0.1700
Data Index: 4188489 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.3134. Min Act: -0.1700
Data Index: 6854446 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.2977. Min Act: -0.1700
Data Index: 1262023 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.3134. Min Act: -0.1700
Data Index: 846419 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.2977. Min Act: -0.1700
Data Index: 5512932 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.2820. Min Act: -0.1700
Data Index: 6194174 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.2820. Min Act: -0.1700
Data Index: 6772824 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.2663. Min Act: -0.1700
Data Index: 1746655 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.2820. Min Act: -0.1700
Data Index: 7885066 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.2663. Min Act: -0.1700
Data Index: 405514 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.2506. Min Act: -0.1700
Data Index: 3791599 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.2663. Min Act: -0.1700
Data Index: 5600467 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.2506. Min Act: -0.1700
Data Index: 2861326 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.2349. Min Act: -0.1700
Data Index: 1595441 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4232. Min Range: -3.4232
Max Act: 3.2506. Min Act: -0.1700
Data Index: 6479670 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19