Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3921 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.3011. Min Act: -0.1700
Data Index: 5513895 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.3011. Min Act: -0.1700
Data Index: 5545157 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.2386. Min Act: -0.1700
Data Index: 8243323 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.2386. Min Act: -0.1700
Data Index: 811616 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.2699. Min Act: -0.1700
Data Index: 7068881 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.2386. Min Act: -0.1700
Data Index: 630155 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.2074. Min Act: -0.1700
Data Index: 8601335 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.2386. Min Act: -0.1700
Data Index: 1391190 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.2386. Min Act: -0.1700
Data Index: 6647966 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.2074. Min Act: -0.1700
Data Index: 6457923 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.1449. Min Act: -0.1700
Data Index: 6717400 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.1449. Min Act: -0.1700
Data Index: 3618247 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.1449. Min Act: -0.1700
Data Index: 4388109 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.1136. Min Act: -0.1700
Data Index: 2467877 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.1136. Min Act: -0.1700
Data Index: 6387529 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.1449. Min Act: -0.1700
Data Index: 8760118 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.0824. Min Act: -0.1700
Data Index: 702092 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.0824. Min Act: -0.1700
Data Index: 2851317 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.0824. Min Act: -0.1700
Data Index: 4160816 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3011. Min Range: -5.3011
Max Act: 5.0511. Min Act: -0.1700
Data Index: 2468539 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19