Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.5030. Min Act: -0.1700
Data Index: 2045617 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.4874. Min Act: -0.1700
Data Index: 426261 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.2678. Min Act: -0.1700
Data Index: 3070900 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.2049. Min Act: -0.1700
Data Index: 7380257 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.2207. Min Act: -0.1700
Data Index: 4398798 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.2207. Min Act: -0.1700
Data Index: 5220616 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.2207. Min Act: -0.1700
Data Index: 3121192 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.2049. Min Act: -0.1700
Data Index: 1192455 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.1735. Min Act: -0.1700
Data Index: 5009127 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.1420. Min Act: -0.1700
Data Index: 4438072 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.1735. Min Act: -0.1700
Data Index: 1440221 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.1420. Min Act: -0.1700
Data Index: 724064 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.1420. Min Act: -0.1700
Data Index: 1067553 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.1420. Min Act: -0.1700
Data Index: 1634060 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.1577. Min Act: -0.1700
Data Index: 7741055 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.1105. Min Act: -0.1700
Data Index: 5642235 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.1577. Min Act: -0.1700
Data Index: 5970021 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.1263. Min Act: -0.1700
Data Index: 257608 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.0947. Min Act: -0.1700
Data Index: 3070895 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5030. Min Range: -3.5030
Max Act: 3.1420. Min Act: -0.1700
Data Index: 2425389 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19