Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4829 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.5432. Min Act: -0.1700
Data Index: 6410448 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.3870. Min Act: -0.1700
Data Index: 2988254 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.3245. Min Act: -0.1700
Data Index: 8389549 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.2932. Min Act: -0.1700
Data Index: 5165986 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.2620. Min Act: -0.1700
Data Index: 7235057 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.1995. Min Act: -0.1700
Data Index: 4571066 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.2307. Min Act: -0.1700
Data Index: 8306519 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.1995. Min Act: -0.1700
Data Index: 7782034 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.1682. Min Act: -0.1700
Data Index: 2329838 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.1995. Min Act: -0.1700
Data Index: 7896454 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.1682. Min Act: -0.1700
Data Index: 7896457 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.1682. Min Act: -0.1700
Data Index: 5194654 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.1995. Min Act: -0.1700
Data Index: 6892858 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.0744. Min Act: -0.1700
Data Index: 1705525 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.0432. Min Act: -0.1700
Data Index: 354027 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.0432. Min Act: -0.1700
Data Index: 3925830 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.0432. Min Act: -0.1700
Data Index: 1109816 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.0432. Min Act: -0.1700
Data Index: 5487691 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.0119. Min Act: -0.1700
Data Index: 1910679 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5432. Min Range: -4.5432
Max Act: 4.0119. Min Act: -0.1700
Data Index: 3613679 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19