Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 59 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2621. Min Range: -6.2621
Max Act: 6.2621. Min Act: -0.1700
Data Index: 3882418 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.9809. Min Act: -0.1700
Data Index: 7149368 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.9809. Min Act: -0.1700
Data Index: 1813591 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.9809. Min Act: -0.1700
Data Index: 6824676 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.9184. Min Act: -0.1700
Data Index: 5314236 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.9496. Min Act: -0.1700
Data Index: 1432373 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.9184. Min Act: -0.1700
Data Index: 5377691 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.9184. Min Act: -0.1700
Data Index: 2906759 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.9184. Min Act: -0.1700
Data Index: 6740003 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.9184. Min Act: -0.1700
Data Index: 4133617 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.8871. Min Act: -0.1700
Data Index: 8116952 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.8871. Min Act: -0.1700
Data Index: 8667513 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.8871. Min Act: -0.1700
Data Index: 8076874 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.8559. Min Act: -0.1700
Data Index: 7897661 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.8559. Min Act: -0.1700
Data Index: 1777794 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.8246. Min Act: -0.1700
Data Index: 3852232 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.8246. Min Act: -0.1700
Data Index: 11253 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.8246. Min Act: -0.1700
Data Index: 3602991 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.7934. Min Act: -0.1700
Data Index: 5006813 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2621. Min Range: -6.2621
Max Act: 5.7934. Min Act: -0.1700
Data Index: 6838884 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19