Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 864 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.4594. Min Act: -0.1700
Data Index: 8260707 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.3656. Min Act: -0.1700
Data Index: 5663664 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.3031. Min Act: -0.1700
Data Index: 7382137 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.1156. Min Act: -0.1700
Data Index: 3275722 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.1469. Min Act: -0.1700
Data Index: 4954670 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.1156. Min Act: -0.1700
Data Index: 4238441 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.1156. Min Act: -0.1700
Data Index: 7967375 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.0844. Min Act: -0.1700
Data Index: 1650038 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.0844. Min Act: -0.1700
Data Index: 2457928 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.0844. Min Act: -0.1700
Data Index: 8196240 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.0531. Min Act: -0.1700
Data Index: 281330 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.0531. Min Act: -0.1700
Data Index: 4198919 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.0531. Min Act: -0.1700
Data Index: 8685292 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.0531. Min Act: -0.1700
Data Index: 3965840 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.0531. Min Act: -0.1700
Data Index: 8072393 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.0218. Min Act: -0.1700
Data Index: 4561086 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.0218. Min Act: -0.1700
Data Index: 7576942 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.0218. Min Act: -0.1700
Data Index: 6982610 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4594. Min Range: -4.4594
Max Act: 3.9906. Min Act: -0.1700
Data Index: 1903192 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4594. Min Range: -4.4594
Max Act: 4.0218. Min Act: -0.1700
Data Index: 2089970 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19