Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3271 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.4401. Min Act: -0.1700
Data Index: 4091910 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.3464. Min Act: -0.1700
Data Index: 151050 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.3776. Min Act: -0.1700
Data Index: 8072941 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.1901. Min Act: -0.1700
Data Index: 8257783 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.1901. Min Act: -0.1700
Data Index: 6408220 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.1589. Min Act: -0.1700
Data Index: 5351878 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.1589. Min Act: -0.1700
Data Index: 7727813 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.1589. Min Act: -0.1700
Data Index: 384344 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.0651. Min Act: -0.1700
Data Index: 1570058 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.0339. Min Act: -0.1700
Data Index: 5923581 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.0339. Min Act: -0.1700
Data Index: 1892609 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4401. Min Range: -6.4401
Max Act: 5.9714. Min Act: -0.1700
Data Index: 2363740 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.0026. Min Act: -0.1700
Data Index: 7164870 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4401. Min Range: -6.4401
Max Act: 5.9714. Min Act: -0.1700
Data Index: 3128327 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4401. Min Range: -6.4401
Max Act: 5.9401. Min Act: -0.1700
Data Index: 3611104 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4401. Min Range: -6.4401
Max Act: 6.0026. Min Act: -0.1700
Data Index: 856161 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4401. Min Range: -6.4401
Max Act: 5.9401. Min Act: -0.1700
Data Index: 1247251 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4401. Min Range: -6.4401
Max Act: 5.8776. Min Act: -0.1700
Data Index: 271932 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4401. Min Range: -6.4401
Max Act: 5.8776. Min Act: -0.1700
Data Index: 4306310 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4401. Min Range: -6.4401
Max Act: 5.8776. Min Act: -0.1700
Data Index: 6522637 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19