Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 331 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0099. Min Range: -7.0099
Max Act: 7.0099. Min Act: -0.1700
Data Index: 4475936 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.8224. Min Act: -0.1700
Data Index: 5378457 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.6974. Min Act: -0.1700
Data Index: 7284056 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.6037. Min Act: -0.1700
Data Index: 2161294 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.6037. Min Act: -0.1700
Data Index: 526353 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.6037. Min Act: -0.1700
Data Index: 6198950 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.6037. Min Act: -0.1700
Data Index: 3256384 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.5724. Min Act: -0.1700
Data Index: 3030845 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.5412. Min Act: -0.1700
Data Index: 6110638 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.5412. Min Act: -0.1700
Data Index: 4314800 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.5099. Min Act: -0.1700
Data Index: 1753170 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.4474. Min Act: -0.1700
Data Index: 5258226 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.4474. Min Act: -0.1700
Data Index: 7710537 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.4162. Min Act: -0.1700
Data Index: 4584788 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.3849. Min Act: -0.1700
Data Index: 4181055 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.3849. Min Act: -0.1700
Data Index: 3368596 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.3849. Min Act: -0.1700
Data Index: 5307378 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.3849. Min Act: -0.1700
Data Index: 2256069 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.3849. Min Act: -0.1700
Data Index: 1241280 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0099. Min Range: -7.0099
Max Act: 6.3537. Min Act: -0.1700
Data Index: 7619619 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19