Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2418 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.2985. Min Act: -0.1700
Data Index: 4532031 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.2672. Min Act: -0.1700
Data Index: 8610707 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.2047. Min Act: -0.1700
Data Index: 2336060 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.2360. Min Act: -0.1700
Data Index: 6820468 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.1110. Min Act: -0.1700
Data Index: 5750296 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.2047. Min Act: -0.1700
Data Index: 7517166 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.1735. Min Act: -0.1700
Data Index: 6635879 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.0797. Min Act: -0.1700
Data Index: 716044 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.1422. Min Act: -0.1700
Data Index: 2333368 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.0797. Min Act: -0.1700
Data Index: 1360752 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.0797. Min Act: -0.1700
Data Index: 1747109 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.0485. Min Act: -0.1700
Data Index: 7193552 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.0485. Min Act: -0.1700
Data Index: 6727273 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.0485. Min Act: -0.1700
Data Index: 8377160 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.0485. Min Act: -0.1700
Data Index: 2736771 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.0485. Min Act: -0.1700
Data Index: 5121422 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.0485. Min Act: -0.1700
Data Index: 3076894 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2985. Min Range: -5.2985
Max Act: 4.9860. Min Act: -0.1700
Data Index: 2460578 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2985. Min Range: -5.2985
Max Act: 4.9547. Min Act: -0.1700
Data Index: 277911 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2985. Min Range: -5.2985
Max Act: 5.0172. Min Act: -0.1700
Data Index: 1209708 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19