Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4104 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.5577. Min Act: -0.1700
Data Index: 2532089 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.4952. Min Act: -0.1700
Data Index: 3511487 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.4952. Min Act: -0.1700
Data Index: 739512 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.4952. Min Act: -0.1700
Data Index: 1385446 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.4952. Min Act: -0.1700
Data Index: 7050188 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.4327. Min Act: -0.1700
Data Index: 3729194 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.4327. Min Act: -0.1700
Data Index: 3565384 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.4327. Min Act: -0.1700
Data Index: 2873049 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.4327. Min Act: -0.1700
Data Index: 6011015 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.3702. Min Act: -0.1700
Data Index: 1143957 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.3702. Min Act: -0.1700
Data Index: 861728 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.3702. Min Act: -0.1700
Data Index: 1962564 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.3077. Min Act: -0.1700
Data Index: 2258820 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.3702. Min Act: -0.1700
Data Index: 384913 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.3077. Min Act: -0.1700
Data Index: 1765813 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.3077. Min Act: -0.1700
Data Index: 6193238 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.3077. Min Act: -0.1700
Data Index: 2674029 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.3077. Min Act: -0.1700
Data Index: 3153456 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.2452. Min Act: -0.1700
Data Index: 2326495 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5577. Min Range: -8.5577
Max Act: 8.2452. Min Act: -0.1700
Data Index: 4666411 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19