Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.7174. Min Act: -0.1700
Data Index: 1673477 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.7174. Min Act: -0.1700
Data Index: 1537832 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.5612. Min Act: -0.1700
Data Index: 1787344 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.4987. Min Act: -0.1700
Data Index: 4870185 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.4987. Min Act: -0.1700
Data Index: 3733653 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.4674. Min Act: -0.1700
Data Index: 1537831 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.4362. Min Act: -0.1700
Data Index: 4088194 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.4049. Min Act: -0.1700
Data Index: 3973528 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3424. Min Act: -0.1700
Data Index: 3888043 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3112. Min Act: -0.1700
Data Index: 3888026 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3424. Min Act: -0.1700
Data Index: 3888044 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3424. Min Act: -0.1700
Data Index: 5799944 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3737. Min Act: -0.1700
Data Index: 979084 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3424. Min Act: -0.1700
Data Index: 3888042 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3112. Min Act: -0.1700
Data Index: 8373287 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3112. Min Act: -0.1700
Data Index: 4933847 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.2799. Min Act: -0.1700
Data Index: 3888031 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.2799. Min Act: -0.1700
Data Index: 3319551 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.2174. Min Act: -0.1700
Data Index: 1619136 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.2487. Min Act: -0.1700
Data Index: 1791965 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19