Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3785 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4244. Min Range: -5.4244
Max Act: 5.4244. Min Act: -0.1700
Data Index: 7394954 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4244. Min Range: -5.4244
Max Act: 5.3619. Min Act: -0.1700
Data Index: 2392176 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4244. Min Range: -5.4244
Max Act: 5.3619. Min Act: -0.1700
Data Index: 4224338 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4244. Min Range: -5.4244
Max Act: 5.2681. Min Act: -0.1700
Data Index: 5942620 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4244. Min Range: -5.4244
Max Act: 5.2681. Min Act: -0.1700
Data Index: 5156818 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4244. Min Range: -5.4244
Max Act: 5.2056. Min Act: -0.1700
Data Index: 4532033 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4244. Min Range: -5.4244
Max Act: 5.1119. Min Act: -0.1700
Data Index: 3086999 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4244. Min Range: -5.4244
Max Act: 5.1119. Min Act: -0.1700
Data Index: 7082860 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4244. Min Range: -5.4244
Max Act: 5.0806. Min Act: -0.1700
Data Index: 471247 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4244. Min Range: -5.4244
Max Act: 5.0494. Min Act: -0.1700
Data Index: 6200126 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4244. Min Range: -5.4244
Max Act: 5.0494. Min Act: -0.1700
Data Index: 4149254 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4244. Min Range: -5.4244
Max Act: 5.0181. Min Act: -0.1700
Data Index: 6693621 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4244. Min Range: -5.4244
Max Act: 4.9869. Min Act: -0.1700
Data Index: 8675387 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4244. Min Range: -5.4244
Max Act: 4.9869. Min Act: -0.1700
Data Index: 5778376 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4244. Min Range: -5.4244
Max Act: 4.9556. Min Act: -0.1700
Data Index: 4776255 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4244. Min Range: -5.4244
Max Act: 4.9869. Min Act: -0.1700
Data Index: 5143232 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4244. Min Range: -5.4244
Max Act: 4.9244. Min Act: -0.1700
Data Index: 1857703 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4244. Min Range: -5.4244
Max Act: 4.9244. Min Act: -0.1700
Data Index: 2058768 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4244. Min Range: -5.4244
Max Act: 4.9244. Min Act: -0.1700
Data Index: 3277292 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4244. Min Range: -5.4244
Max Act: 4.9244. Min Act: -0.1700
Data Index: 4024154 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19