Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4974 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.7728. Min Act: -0.1700
Data Index: 2500014 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.7103. Min Act: -0.1700
Data Index: 2112219 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.7103. Min Act: -0.1700
Data Index: 3937749 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.7103. Min Act: -0.1700
Data Index: 2197786 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.6478. Min Act: -0.1700
Data Index: 2686920 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.6165. Min Act: -0.1700
Data Index: 4419534 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.6478. Min Act: -0.1700
Data Index: 4440995 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.6165. Min Act: -0.1700
Data Index: 4672184 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.6165. Min Act: -0.1700
Data Index: 4030575 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.6478. Min Act: -0.1700
Data Index: 2661348 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.5540. Min Act: -0.1700
Data Index: 4683030 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.4915. Min Act: -0.1700
Data Index: 3385215 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.5228. Min Act: -0.1700
Data Index: 7503820 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.5228. Min Act: -0.1700
Data Index: 2588132 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.5228. Min Act: -0.1700
Data Index: 8248674 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.4915. Min Act: -0.1700
Data Index: 4829315 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.4603. Min Act: -0.1700
Data Index: 6153574 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.4603. Min Act: -0.1700
Data Index: 135613 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.4290. Min Act: -0.1700
Data Index: 8105195 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7728. Min Range: -6.7728
Max Act: 6.4603. Min Act: -0.1700
Data Index: 6843327 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19