Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3459 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.1626. Min Act: -0.1700
Data Index: 4868366 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.1313. Min Act: -0.1700
Data Index: 744408 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.1313. Min Act: -0.1700
Data Index: 4868365 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0688. Min Act: -0.1700
Data Index: 2191077 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0376. Min Act: -0.1700
Data Index: 2975832 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0688. Min Act: -0.1700
Data Index: 5181253 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0376. Min Act: -0.1700
Data Index: 3481996 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0376. Min Act: -0.1700
Data Index: 4026504 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0376. Min Act: -0.1700
Data Index: 7713212 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1626. Min Range: -5.1626
Max Act: 5.0063. Min Act: -0.1700
Data Index: 5124662 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.9438. Min Act: -0.1700
Data Index: 5811826 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.9438. Min Act: -0.1700
Data Index: 456750 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.9438. Min Act: -0.1700
Data Index: 1498275 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.9438. Min Act: -0.1700
Data Index: 7350546 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.9438. Min Act: -0.1700
Data Index: 4376330 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.9126. Min Act: -0.1700
Data Index: 8127072 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.9126. Min Act: -0.1700
Data Index: 7369542 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.9126. Min Act: -0.1700
Data Index: 7919212 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.8813. Min Act: -0.1700
Data Index: 551035 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1626. Min Range: -5.1626
Max Act: 4.8813. Min Act: -0.1700
Data Index: 2033704 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19