Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1682 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.6114. Min Act: -0.1700
Data Index: 4157725 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.5489. Min Act: -0.1700
Data Index: 2343890 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.3926. Min Act: -0.1700
Data Index: 7416736 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.3301. Min Act: -0.1700
Data Index: 5730973 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.2989. Min Act: -0.1700
Data Index: 8818675 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.2989. Min Act: -0.1700
Data Index: 4820212 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.2676. Min Act: -0.1700
Data Index: 3148497 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.2989. Min Act: -0.1700
Data Index: 2870264 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.2051. Min Act: -0.1700
Data Index: 3558614 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.1739. Min Act: -0.1700
Data Index: 119960 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.2051. Min Act: -0.1700
Data Index: 818552 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.1426. Min Act: -0.1700
Data Index: 5649352 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.1426. Min Act: -0.1700
Data Index: 3612663 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.1426. Min Act: -0.1700
Data Index: 8424743 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.1114. Min Act: -0.1700
Data Index: 2206215 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.1426. Min Act: -0.1700
Data Index: 8466116 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.0801. Min Act: -0.1700
Data Index: 995921 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.0801. Min Act: -0.1700
Data Index: 3716533 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.0176. Min Act: -0.1700
Data Index: 2048990 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6114. Min Range: -5.6114
Max Act: 5.0489. Min Act: -0.1700
Data Index: 2443810 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19