Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.6809. Min Act: -0.1700
Data Index: 319257 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.6809. Min Act: -0.1700
Data Index: 5154643 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.5559. Min Act: -0.1700
Data Index: 7320956 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.5872. Min Act: -0.1700
Data Index: 583865 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.4622. Min Act: -0.1700
Data Index: 4458925 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.4622. Min Act: -0.1700
Data Index: 598765 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.4309. Min Act: -0.1700
Data Index: 3273506 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3997. Min Act: -0.1700
Data Index: 1062935 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.4309. Min Act: -0.1700
Data Index: 2850363 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.4309. Min Act: -0.1700
Data Index: 1239550 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.4309. Min Act: -0.1700
Data Index: 8176554 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.4309. Min Act: -0.1700
Data Index: 6384642 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.4309. Min Act: -0.1700
Data Index: 1229096 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3997. Min Act: -0.1700
Data Index: 1152745 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3997. Min Act: -0.1700
Data Index: 1062357 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3684. Min Act: -0.1700
Data Index: 6010745 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3684. Min Act: -0.1700
Data Index: 6157050 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3997. Min Act: -0.1700
Data Index: 3212833 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3684. Min Act: -0.1700
Data Index: 603530 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3372. Min Act: -0.1700
Data Index: 6872701 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19