Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1144 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.8276. Min Act: -0.1700
Data Index: 2334804 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.6401. Min Act: -0.1700
Data Index: 5609250 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.6401. Min Act: -0.1700
Data Index: 2272367 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5776. Min Act: -0.1700
Data Index: 1811260 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5463. Min Act: -0.1700
Data Index: 6529236 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5151. Min Act: -0.1700
Data Index: 6179245 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5151. Min Act: -0.1700
Data Index: 4604681 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5151. Min Act: -0.1700
Data Index: 1189305 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5151. Min Act: -0.1700
Data Index: 7979795 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.4838. Min Act: -0.1700
Data Index: 5178395 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.4526. Min Act: -0.1700
Data Index: 8327566 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.4838. Min Act: -0.1700
Data Index: 1592299 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.4838. Min Act: -0.1700
Data Index: 2630272 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.4526. Min Act: -0.1700
Data Index: 3021314 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.4526. Min Act: -0.1700
Data Index: 2369088 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.4526. Min Act: -0.1700
Data Index: 196225 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.4213. Min Act: -0.1700
Data Index: 7995150 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.3588. Min Act: -0.1700
Data Index: 6539678 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.3901. Min Act: -0.1700
Data Index: 8240253 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.3901. Min Act: -0.1700
Data Index: 6109004 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19