Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.6469. Min Act: -0.1700
Data Index: 684720 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.4594. Min Act: -0.1700
Data Index: 2507287 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.3656. Min Act: -0.1700
Data Index: 916731 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.2719. Min Act: -0.1700
Data Index: 2312499 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.2719. Min Act: -0.1700
Data Index: 1373663 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.2406. Min Act: -0.1700
Data Index: 6256681 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.2094. Min Act: -0.1700
Data Index: 7118000 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.1469. Min Act: -0.1700
Data Index: 7781476 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.1156. Min Act: -0.1700
Data Index: 5006885 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.0844. Min Act: -0.1700
Data Index: 2899175 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.0531. Min Act: -0.1700
Data Index: 3585624 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.0219. Min Act: -0.1700
Data Index: 4958087 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.0531. Min Act: -0.1700
Data Index: 5016649 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6469. Min Range: -7.6469
Max Act: 7.0219. Min Act: -0.1700
Data Index: 5639920 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6469. Min Range: -7.6469
Max Act: 6.9594. Min Act: -0.1700
Data Index: 7807419 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6469. Min Range: -7.6469
Max Act: 6.9594. Min Act: -0.1700
Data Index: 3470053 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6469. Min Range: -7.6469
Max Act: 6.9594. Min Act: -0.1700
Data Index: 4404807 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6469. Min Range: -7.6469
Max Act: 6.9594. Min Act: -0.1700
Data Index: 2706252 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6469. Min Range: -7.6469
Max Act: 6.9281. Min Act: -0.1700
Data Index: 3708473 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6469. Min Range: -7.6469
Max Act: 6.9594. Min Act: -0.1700
Data Index: 2272303 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19