Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4874 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.9812. Min Act: -0.1700
Data Index: 746350 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0124. Min Range: -5.0124
Max Act: 5.0124. Min Act: -0.1700
Data Index: 6798996 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.9812. Min Act: -0.1700
Data Index: 8487380 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.9499. Min Act: -0.1700
Data Index: 4467446 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.9499. Min Act: -0.1700
Data Index: 4719042 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.8874. Min Act: -0.1700
Data Index: 6750953 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.9187. Min Act: -0.1700
Data Index: 1985134 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.8874. Min Act: -0.1700
Data Index: 2019745 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.8562. Min Act: -0.1700
Data Index: 5122238 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.8562. Min Act: -0.1700
Data Index: 7943989 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.7937. Min Act: -0.1700
Data Index: 4928214 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.8249. Min Act: -0.1700
Data Index: 5553075 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.8249. Min Act: -0.1700
Data Index: 2368367 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.8249. Min Act: -0.1700
Data Index: 7478859 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.8562. Min Act: -0.1700
Data Index: 4326007 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.7937. Min Act: -0.1700
Data Index: 5886008 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.7937. Min Act: -0.1700
Data Index: 3946377 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.7937. Min Act: -0.1700
Data Index: 2902710 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.8249. Min Act: -0.1700
Data Index: 6875890 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0124. Min Range: -5.0124
Max Act: 4.7937. Min Act: -0.1700
Data Index: 7342039 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19