Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5351 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.6236. Min Act: -0.1700
Data Index: 5899025 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.3736. Min Act: -0.1700
Data Index: 5899026 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.3736. Min Act: -0.1700
Data Index: 6533182 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.3111. Min Act: -0.1700
Data Index: 1143868 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.3111. Min Act: -0.1700
Data Index: 1862222 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.3111. Min Act: -0.1700
Data Index: 2177264 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.3111. Min Act: -0.1700
Data Index: 5261647 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2799. Min Act: -0.1700
Data Index: 2797052 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2486. Min Act: -0.1700
Data Index: 4126378 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2799. Min Act: -0.1700
Data Index: 7870006 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2486. Min Act: -0.1700
Data Index: 2214649 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2486. Min Act: -0.1700
Data Index: 5291477 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2486. Min Act: -0.1700
Data Index: 7602495 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2486. Min Act: -0.1700
Data Index: 6008114 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2486. Min Act: -0.1700
Data Index: 1060124 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2174. Min Act: -0.1700
Data Index: 3968953 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2174. Min Act: -0.1700
Data Index: 5111473 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2174. Min Act: -0.1700
Data Index: 1774032 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2174. Min Act: -0.1700
Data Index: 6142350 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6236. Min Range: -5.6236
Max Act: 5.2174. Min Act: -0.1700
Data Index: 5626046 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19