Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 641 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.8177. Min Act: -0.1700
Data Index: 6250593 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.7240. Min Act: -0.1700
Data Index: 5517142 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.6615. Min Act: -0.1700
Data Index: 2872211 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.5677. Min Act: -0.1700
Data Index: 8292268 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.5677. Min Act: -0.1700
Data Index: 5654359 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.5365. Min Act: -0.1700
Data Index: 8010374 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.5052. Min Act: -0.1700
Data Index: 3439045 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.5052. Min Act: -0.1700
Data Index: 1258071 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.4740. Min Act: -0.1700
Data Index: 2428049 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.4740. Min Act: -0.1700
Data Index: 1655849 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.4115. Min Act: -0.1700
Data Index: 4091725 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.4427. Min Act: -0.1700
Data Index: 2809594 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.4115. Min Act: -0.1700
Data Index: 6635270 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.3802. Min Act: -0.1700
Data Index: 2926312 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.4115. Min Act: -0.1700
Data Index: 3828719 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.3802. Min Act: -0.1700
Data Index: 3977725 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.3802. Min Act: -0.1700
Data Index: 655828 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.3490. Min Act: -0.1700
Data Index: 4560214 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.3490. Min Act: -0.1700
Data Index: 1812132 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8177. Min Range: -5.8177
Max Act: 5.3490. Min Act: -0.1700
Data Index: 7424863 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19