Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.6809. Min Act: -0.1700
Data Index: 292210 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.5559. Min Act: -0.1700
Data Index: 7785698 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.4309. Min Act: -0.1700
Data Index: 2997165 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3997. Min Act: -0.1700
Data Index: 4963050 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3997. Min Act: -0.1700
Data Index: 5295363 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3997. Min Act: -0.1700
Data Index: 7795033 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3372. Min Act: -0.1700
Data Index: 7203982 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3684. Min Act: -0.1700
Data Index: 5403666 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3059. Min Act: -0.1700
Data Index: 2157546 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3059. Min Act: -0.1700
Data Index: 4485231 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.3059. Min Act: -0.1700
Data Index: 5887369 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.2747. Min Act: -0.1700
Data Index: 19500 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.2747. Min Act: -0.1700
Data Index: 4559584 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.2747. Min Act: -0.1700
Data Index: 1336159 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.2434. Min Act: -0.1700
Data Index: 5571622 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.2122. Min Act: -0.1700
Data Index: 8628583 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.2434. Min Act: -0.1700
Data Index: 2111645 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.2434. Min Act: -0.1700
Data Index: 820350 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.2122. Min Act: -0.1700
Data Index: 6544405 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6809. Min Range: -5.6809
Max Act: 5.2434. Min Act: -0.1700
Data Index: 1480537 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19