Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0132. Min Range: -7.0132
Max Act: 7.0132. Min Act: -0.1700
Data Index: 1992506 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.7319. Min Act: -0.1700
Data Index: 7634595 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.7319. Min Act: -0.1700
Data Index: 5443711 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.6069. Min Act: -0.1700
Data Index: 8453347 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.5757. Min Act: -0.1700
Data Index: 5204035 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.5132. Min Act: -0.1700
Data Index: 2321170 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.4819. Min Act: -0.1700
Data Index: 445673 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.4507. Min Act: -0.1700
Data Index: 5065778 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.4507. Min Act: -0.1700
Data Index: 8111694 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.3882. Min Act: -0.1700
Data Index: 8331587 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.3882. Min Act: -0.1700
Data Index: 3119632 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.3569. Min Act: -0.1700
Data Index: 6441919 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.3569. Min Act: -0.1700
Data Index: 6823832 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.3257. Min Act: -0.1700
Data Index: 5279099 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.2944. Min Act: -0.1700
Data Index: 3788160 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.2944. Min Act: -0.1700
Data Index: 6330121 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.2944. Min Act: -0.1700
Data Index: 3146323 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.2632. Min Act: -0.1700
Data Index: 3932997 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.2319. Min Act: -0.1700
Data Index: 2998108 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0132. Min Range: -7.0132
Max Act: 6.2319. Min Act: -0.1700
Data Index: 3139109 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19