Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2352 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.8125. Min Act: -0.1700
Data Index: 4429266 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.7188. Min Act: -0.1700
Data Index: 7343032 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.6563. Min Act: -0.1700
Data Index: 326494 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.6250. Min Act: -0.1700
Data Index: 784310 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.5313. Min Act: -0.1700
Data Index: 2584030 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.3750. Min Act: -0.1700
Data Index: 8695284 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.3125. Min Act: -0.1700
Data Index: 7238765 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.2500. Min Act: -0.1700
Data Index: 3876048 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.2500. Min Act: -0.1700
Data Index: 5148335 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.2188. Min Act: -0.1700
Data Index: 7164125 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.1563. Min Act: -0.1700
Data Index: 6198680 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.1250. Min Act: -0.1700
Data Index: 97488 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.0938. Min Act: -0.1700
Data Index: 609567 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.0625. Min Act: -0.1700
Data Index: 3566403 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.0625. Min Act: -0.1700
Data Index: 4482336 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.0313. Min Act: -0.1700
Data Index: 1526897 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.0000. Min Act: -0.1700
Data Index: 6078205 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8125. Min Range: -7.8125
Max Act: 7.0000. Min Act: -0.1700
Data Index: 3086795 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8125. Min Range: -7.8125
Max Act: 6.9688. Min Act: -0.1700
Data Index: 721930 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8125. Min Range: -7.8125
Max Act: 6.9688. Min Act: -0.1700
Data Index: 1344512 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19