Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1169 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.9700. Min Act: -0.1700
Data Index: 871433 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.8450. Min Act: -0.1700
Data Index: 695157 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.5012. Min Act: -0.1700
Data Index: 1444712 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.4075. Min Act: -0.1700
Data Index: 2098575 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.3762. Min Act: -0.1700
Data Index: 3975292 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.2825. Min Act: -0.1700
Data Index: 1309798 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.3450. Min Act: -0.1700
Data Index: 837619 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.2825. Min Act: -0.1700
Data Index: 3477625 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.1887. Min Act: -0.1700
Data Index: 8108331 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.1887. Min Act: -0.1700
Data Index: 1821381 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.1262. Min Act: -0.1700
Data Index: 7250356 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.0637. Min Act: -0.1700
Data Index: 3544216 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.0012. Min Act: -0.1700
Data Index: 3302018 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.0325. Min Act: -0.1700
Data Index: 5140511 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.0325. Min Act: -0.1700
Data Index: 57080 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.0012. Min Act: -0.1700
Data Index: 118413 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.0012. Min Act: -0.1700
Data Index: 549553 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9700. Min Range: -7.9700
Max Act: 7.0012. Min Act: -0.1700
Data Index: 6298219 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9700. Min Range: -7.9700
Max Act: 6.9387. Min Act: -0.1700
Data Index: 4839265 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9700. Min Range: -7.9700
Max Act: 6.9075. Min Act: -0.1700
Data Index: 5100747 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19