Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3611 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.6710. Min Act: -0.1700
Data Index: 8492874 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.4210. Min Act: -0.1700
Data Index: 7607276 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.3897. Min Act: -0.1700
Data Index: 4876336 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.3272. Min Act: -0.1700
Data Index: 6013908 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.2022. Min Act: -0.1700
Data Index: 6570427 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.1397. Min Act: -0.1700
Data Index: 4290169 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.1710. Min Act: -0.1700
Data Index: 3488153 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.1085. Min Act: -0.1700
Data Index: 3260516 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.1085. Min Act: -0.1700
Data Index: 1734489 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.1085. Min Act: -0.1700
Data Index: 7246726 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.0772. Min Act: -0.1700
Data Index: 6043243 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.0460. Min Act: -0.1700
Data Index: 4542028 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.0460. Min Act: -0.1700
Data Index: 7426934 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.0460. Min Act: -0.1700
Data Index: 6099090 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.0460. Min Act: -0.1700
Data Index: 7535164 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.0460. Min Act: -0.1700
Data Index: 7864754 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.0460. Min Act: -0.1700
Data Index: 6885862 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6710. Min Range: -5.6710
Max Act: 5.0147. Min Act: -0.1700
Data Index: 5462401 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6710. Min Range: -5.6710
Max Act: 4.9522. Min Act: -0.1700
Data Index: 6638345 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6710. Min Range: -5.6710
Max Act: 4.9835. Min Act: -0.1700
Data Index: 2163246 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19