Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1064 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.5068. Min Act: -0.1700
Data Index: 1717277 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.5068. Min Act: -0.1700
Data Index: 4248259 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.5068. Min Act: -0.1700
Data Index: 2491000 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.3505. Min Act: -0.1700
Data Index: 4851292 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.3193. Min Act: -0.1700
Data Index: 4738553 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.2880. Min Act: -0.1700
Data Index: 3007220 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.2880. Min Act: -0.1700
Data Index: 532445 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.2255. Min Act: -0.1700
Data Index: 2567039 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.2255. Min Act: -0.1700
Data Index: 7394572 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.2255. Min Act: -0.1700
Data Index: 7003535 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.2568. Min Act: -0.1700
Data Index: 452839 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.2568. Min Act: -0.1700
Data Index: 3332519 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.2568. Min Act: -0.1700
Data Index: 6372599 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.1630. Min Act: -0.1700
Data Index: 6470946 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.1943. Min Act: -0.1700
Data Index: 2024057 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.1943. Min Act: -0.1700
Data Index: 3797315 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.1630. Min Act: -0.1700
Data Index: 1140020 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.1318. Min Act: -0.1700
Data Index: 1298534 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.1943. Min Act: -0.1700
Data Index: 2963424 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5068. Min Range: -5.5068
Max Act: 5.1630. Min Act: -0.1700
Data Index: 3896316 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19