Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 493 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1380. Min Range: -6.1380
Max Act: 6.1380. Min Act: -0.1700
Data Index: 5746065 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1380. Min Range: -6.1380
Max Act: 5.1067. Min Act: -0.1700
Data Index: 6741127 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1380. Min Range: -6.1380
Max Act: 5.0755. Min Act: -0.1700
Data Index: 2508714 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1380. Min Range: -6.1380
Max Act: 5.0755. Min Act: -0.1700
Data Index: 2492019 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1380. Min Range: -6.1380
Max Act: 5.0130. Min Act: -0.1700
Data Index: 774442 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1380. Min Range: -6.1380
Max Act: 5.0130. Min Act: -0.1700
Data Index: 5034213 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1380. Min Range: -6.1380
Max Act: 5.0130. Min Act: -0.1700
Data Index: 566747 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1380. Min Range: -6.1380
Max Act: 5.0130. Min Act: -0.1700
Data Index: 8785417 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1380. Min Range: -6.1380
Max Act: 4.9817. Min Act: -0.1700
Data Index: 5039134 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1380. Min Range: -6.1380
Max Act: 4.9817. Min Act: -0.1700
Data Index: 3070260 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1380. Min Range: -6.1380
Max Act: 4.9505. Min Act: -0.1700
Data Index: 5642662 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1380. Min Range: -6.1380
Max Act: 4.9817. Min Act: -0.1700
Data Index: 3070261 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1380. Min Range: -6.1380
Max Act: 4.9505. Min Act: -0.1700
Data Index: 104062 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1380. Min Range: -6.1380
Max Act: 4.9505. Min Act: -0.1700
Data Index: 6462365 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1380. Min Range: -6.1380
Max Act: 4.9505. Min Act: -0.1700
Data Index: 7550304 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1380. Min Range: -6.1380
Max Act: 4.8880. Min Act: -0.1700
Data Index: 8308540 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1380. Min Range: -6.1380
Max Act: 4.9192. Min Act: -0.1700
Data Index: 672142 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1380. Min Range: -6.1380
Max Act: 4.8880. Min Act: -0.1700
Data Index: 3877748 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1380. Min Range: -6.1380
Max Act: 4.8880. Min Act: -0.1700
Data Index: 6189649 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1380. Min Range: -6.1380
Max Act: 4.8567. Min Act: -0.1700
Data Index: 1754759 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19