Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5325 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1202. Min Range: -7.1202
Max Act: 7.1202. Min Act: -0.1700
Data Index: 7814086 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.8077. Min Act: -0.1700
Data Index: 4797014 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.7452. Min Act: -0.1700
Data Index: 2289128 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.5577. Min Act: -0.1700
Data Index: 1089822 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.4327. Min Act: -0.1700
Data Index: 7601600 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.4952. Min Act: -0.1700
Data Index: 868918 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.4015. Min Act: -0.1700
Data Index: 4949332 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.4015. Min Act: -0.1700
Data Index: 4966414 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.3390. Min Act: -0.1700
Data Index: 5901795 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.3077. Min Act: -0.1700
Data Index: 6552880 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2452. Min Act: -0.1700
Data Index: 6978640 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2452. Min Act: -0.1700
Data Index: 1641058 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2140. Min Act: -0.1700
Data Index: 8027445 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2140. Min Act: -0.1700
Data Index: 3762323 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2140. Min Act: -0.1700
Data Index: 6440403 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2140. Min Act: -0.1700
Data Index: 7218094 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2140. Min Act: -0.1700
Data Index: 5499294 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2140. Min Act: -0.1700
Data Index: 5318834 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.1515. Min Act: -0.1700
Data Index: 7489882 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.1202. Min Act: -0.1700
Data Index: 6661561 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19