Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9446. Min Range: -9.9446
Max Act: 9.9446. Min Act: -0.1700
Data Index: 6386172 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9446. Min Range: -9.9446
Max Act: 9.4446. Min Act: -0.1700
Data Index: 3434234 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9446. Min Range: -9.9446
Max Act: 9.1321. Min Act: -0.1700
Data Index: 2005208 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9446. Min Range: -9.9446
Max Act: 9.1321. Min Act: -0.1700
Data Index: 6063420 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9446. Min Range: -9.9446
Max Act: 9.1321. Min Act: -0.1700
Data Index: 2552843 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.8821. Min Act: -0.1700
Data Index: 2005205 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.7571. Min Act: -0.1700
Data Index: 6075663 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.7571. Min Act: -0.1700
Data Index: 788798 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.7571. Min Act: -0.1700
Data Index: 393890 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.6946. Min Act: -0.1700
Data Index: 6955132 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.6946. Min Act: -0.1700
Data Index: 4438915 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.6946. Min Act: -0.1700
Data Index: 3489740 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.6321. Min Act: -0.1700
Data Index: 221030 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.5071. Min Act: -0.1700
Data Index: 5991259 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.6321. Min Act: -0.1700
Data Index: 5866243 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.5696. Min Act: -0.1700
Data Index: 2914852 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.5696. Min Act: -0.1700
Data Index: 6075656 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.5071. Min Act: -0.1700
Data Index: 2315637 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.5071. Min Act: -0.1700
Data Index: 2051772 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9446. Min Range: -9.9446
Max Act: 8.4446. Min Act: -0.1700
Data Index: 6271179 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19