Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2235. Min Range: -5.2235
Max Act: 5.2235. Min Act: -0.1700
Data Index: 8587781 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.7860. Min Act: -0.1700
Data Index: 342747 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.6610. Min Act: -0.1700
Data Index: 3342612 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.6610. Min Act: -0.1700
Data Index: 4154839 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.5673. Min Act: -0.1700
Data Index: 2117671 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.5360. Min Act: -0.1700
Data Index: 8582137 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.5360. Min Act: -0.1700
Data Index: 4348171 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.5360. Min Act: -0.1700
Data Index: 8366739 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.4735. Min Act: -0.1700
Data Index: 2117672 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.4735. Min Act: -0.1700
Data Index: 6931141 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.4423. Min Act: -0.1700
Data Index: 1399877 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.4110. Min Act: -0.1700
Data Index: 6653564 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.4110. Min Act: -0.1700
Data Index: 4797645 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.4423. Min Act: -0.1700
Data Index: 499032 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.3798. Min Act: -0.1700
Data Index: 7261460 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.3798. Min Act: -0.1700
Data Index: 6717142 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.3798. Min Act: -0.1700
Data Index: 4797646 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.4110. Min Act: -0.1700
Data Index: 2699647 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.3172. Min Act: -0.1700
Data Index: 3152896 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2235. Min Range: -5.2235
Max Act: 4.3485. Min Act: -0.1700
Data Index: 6737316 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19