Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 617 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2177. Min Range: -5.2177
Max Act: 5.2177. Min Act: -0.1700
Data Index: 8710440 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2177. Min Range: -5.2177
Max Act: 5.1865. Min Act: -0.1700
Data Index: 5240744 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2177. Min Range: -5.2177
Max Act: 5.0302. Min Act: -0.1700
Data Index: 2012384 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.9990. Min Act: -0.1700
Data Index: 1402689 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.9990. Min Act: -0.1700
Data Index: 3978213 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.9990. Min Act: -0.1700
Data Index: 545933 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.9365. Min Act: -0.1700
Data Index: 2288305 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.9365. Min Act: -0.1700
Data Index: 4415402 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.9052. Min Act: -0.1700
Data Index: 2721688 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.9052. Min Act: -0.1700
Data Index: 3999022 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.9052. Min Act: -0.1700
Data Index: 3552558 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.8427. Min Act: -0.1700
Data Index: 8756827 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.8740. Min Act: -0.1700
Data Index: 725691 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.8740. Min Act: -0.1700
Data Index: 47776 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.8740. Min Act: -0.1700
Data Index: 907281 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.8740. Min Act: -0.1700
Data Index: 8514657 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.8115. Min Act: -0.1700
Data Index: 2406853 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.8115. Min Act: -0.1700
Data Index: 1460447 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.8115. Min Act: -0.1700
Data Index: 2487493 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2177. Min Range: -5.2177
Max Act: 4.8115. Min Act: -0.1700
Data Index: 432646 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19