Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.6318. Min Act: -0.1700
Data Index: 3451886 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.3818. Min Act: -0.1700
Data Index: 4156232 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.3818. Min Act: -0.1700
Data Index: 4930896 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.3193. Min Act: -0.1700
Data Index: 1368876 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.2568. Min Act: -0.1700
Data Index: 2208369 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.2568. Min Act: -0.1700
Data Index: 4301954 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.1943. Min Act: -0.1700
Data Index: 2267427 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.1943. Min Act: -0.1700
Data Index: 428140 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.2255. Min Act: -0.1700
Data Index: 106710 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.1943. Min Act: -0.1700
Data Index: 4005573 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.1630. Min Act: -0.1700
Data Index: 6809081 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.1318. Min Act: -0.1700
Data Index: 7567303 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.1630. Min Act: -0.1700
Data Index: 224814 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.1630. Min Act: -0.1700
Data Index: 1542878 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.1318. Min Act: -0.1700
Data Index: 1736575 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.1005. Min Act: -0.1700
Data Index: 3533230 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.1005. Min Act: -0.1700
Data Index: 8641158 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.0380. Min Act: -0.1700
Data Index: 5342168 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.0380. Min Act: -0.1700
Data Index: 8201911 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6318. Min Range: -7.6318
Max Act: 7.1005. Min Act: -0.1700
Data Index: 6853910 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19