Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3784 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.2782. Min Act: -0.1700
Data Index: 4211892 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.3095. Min Act: -0.1700
Data Index: 6824967 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.2157. Min Act: -0.1700
Data Index: 683761 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.1845. Min Act: -0.1700
Data Index: 3174020 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.1845. Min Act: -0.1700
Data Index: 7382348 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.0907. Min Act: -0.1700
Data Index: 6559275 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.1532. Min Act: -0.1700
Data Index: 3726905 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.0907. Min Act: -0.1700
Data Index: 3028594 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.0907. Min Act: -0.1700
Data Index: 3335926 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.1220. Min Act: -0.1700
Data Index: 3208598 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.1220. Min Act: -0.1700
Data Index: 7279086 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.0907. Min Act: -0.1700
Data Index: 8599370 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.0907. Min Act: -0.1700
Data Index: 3908697 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.0282. Min Act: -0.1700
Data Index: 8633340 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3095. Min Range: -5.3095
Max Act: 4.9970. Min Act: -0.1700
Data Index: 3335927 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3095. Min Range: -5.3095
Max Act: 4.9970. Min Act: -0.1700
Data Index: 4868020 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3095. Min Range: -5.3095
Max Act: 4.9345. Min Act: -0.1700
Data Index: 2633847 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3095. Min Range: -5.3095
Max Act: 4.9657. Min Act: -0.1700
Data Index: 7211604 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.0282. Min Act: -0.1700
Data Index: 2787962 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3095. Min Range: -5.3095
Max Act: 5.0282. Min Act: -0.1700
Data Index: 3745256 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19