Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1000 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.9982. Min Act: -0.1700
Data Index: 3383795 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.9670. Min Act: -0.1700
Data Index: 794511 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.9357. Min Act: -0.1700
Data Index: 6836072 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.9045. Min Act: -0.1700
Data Index: 1589279 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.8732. Min Act: -0.1700
Data Index: 574138 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.9045. Min Act: -0.1700
Data Index: 5096711 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.7795. Min Act: -0.1700
Data Index: 5591079 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.7482. Min Act: -0.1700
Data Index: 3878621 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.7482. Min Act: -0.1700
Data Index: 1200447 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.7482. Min Act: -0.1700
Data Index: 3389998 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.7170. Min Act: -0.1700
Data Index: 7172667 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.7482. Min Act: -0.1700
Data Index: 1589277 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.7170. Min Act: -0.1700
Data Index: 4489402 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.6857. Min Act: -0.1700
Data Index: 5537834 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.6857. Min Act: -0.1700
Data Index: 8296561 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.6857. Min Act: -0.1700
Data Index: 194943 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.6857. Min Act: -0.1700
Data Index: 2267593 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.6857. Min Act: -0.1700
Data Index: 6589706 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.7170. Min Act: -0.1700
Data Index: 5591590 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.6545. Min Act: -0.1700
Data Index: 5174297 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19