Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 957 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.6731. Min Act: -0.1700
Data Index: 258783 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.4856. Min Act: -0.1700
Data Index: 6172976 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.4543. Min Act: -0.1700
Data Index: 1714694 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.4231. Min Act: -0.1700
Data Index: 5598621 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.3606. Min Act: -0.1700
Data Index: 6771973 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.3293. Min Act: -0.1700
Data Index: 2001367 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.3293. Min Act: -0.1700
Data Index: 4221008 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.3293. Min Act: -0.1700
Data Index: 8631659 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.3293. Min Act: -0.1700
Data Index: 2001366 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.2668. Min Act: -0.1700
Data Index: 4571719 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.3293. Min Act: -0.1700
Data Index: 3861633 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.2668. Min Act: -0.1700
Data Index: 8684400 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.2668. Min Act: -0.1700
Data Index: 3287612 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.2356. Min Act: -0.1700
Data Index: 3972375 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.2043. Min Act: -0.1700
Data Index: 334869 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.2043. Min Act: -0.1700
Data Index: 4455196 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.2043. Min Act: -0.1700
Data Index: 6419899 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.2356. Min Act: -0.1700
Data Index: 1578660 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.1731. Min Act: -0.1700
Data Index: 5875962 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6731. Min Range: -6.6731
Max Act: 6.1731. Min Act: -0.1700
Data Index: 3034323 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19