Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2840 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.9283. Min Act: -0.1700
Data Index: 2612032 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.9124. Min Act: -0.1700
Data Index: 7371817 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.8489. Min Act: -0.1700
Data Index: 2842205 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.8330. Min Act: -0.1700
Data Index: 6841626 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.8171. Min Act: -0.1700
Data Index: 5128563 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.8171. Min Act: -0.1700
Data Index: 5747479 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7853. Min Act: -0.1700
Data Index: 3071753 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7853. Min Act: -0.1700
Data Index: 4113820 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7693. Min Act: -0.1700
Data Index: 1207473 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7534. Min Act: -0.1700
Data Index: 4604811 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7693. Min Act: -0.1700
Data Index: 2763783 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7374. Min Act: -0.1700
Data Index: 4113821 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7214. Min Act: -0.1700
Data Index: 4913593 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7214. Min Act: -0.1700
Data Index: 6751276 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7214. Min Act: -0.1700
Data Index: 3950376 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7214. Min Act: -0.1700
Data Index: 1916955 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7214. Min Act: -0.1700
Data Index: 4604812 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7055. Min Act: -0.1700
Data Index: 4945511 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7055. Min Act: -0.1700
Data Index: 2386886 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9283. Min Range: -2.9283
Max Act: 2.7055. Min Act: -0.1700
Data Index: 3123450 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19