Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.7220. Min Act: -0.1700
Data Index: 4763499 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.4720. Min Act: -0.1700
Data Index: 4958381 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.4407. Min Act: -0.1700
Data Index: 738880 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.4095. Min Act: -0.1700
Data Index: 55870 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.3157. Min Act: -0.1700
Data Index: 3612040 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.3157. Min Act: -0.1700
Data Index: 8002611 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.1907. Min Act: -0.1700
Data Index: 3629212 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.2220. Min Act: -0.1700
Data Index: 8663371 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.1282. Min Act: -0.1700
Data Index: 4759572 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.1595. Min Act: -0.1700
Data Index: 3689159 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.1282. Min Act: -0.1700
Data Index: 5457343 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.1282. Min Act: -0.1700
Data Index: 5715882 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.0970. Min Act: -0.1700
Data Index: 3748103 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.0970. Min Act: -0.1700
Data Index: 6281983 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.0657. Min Act: -0.1700
Data Index: 5387318 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.0345. Min Act: -0.1700
Data Index: 7020726 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.0345. Min Act: -0.1700
Data Index: 6342913 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.0345. Min Act: -0.1700
Data Index: 2172161 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.0032. Min Act: -0.1700
Data Index: 4417823 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7220. Min Range: -5.7220
Max Act: 5.0032. Min Act: -0.1700
Data Index: 2058517 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19