Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2479 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2527. Min Range: -7.2527
Max Act: 7.2527. Min Act: -0.1700
Data Index: 7255026 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2527. Min Range: -7.2527
Max Act: 7.2527. Min Act: -0.1700
Data Index: 4969494 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2527. Min Range: -7.2527
Max Act: 7.1902. Min Act: -0.1700
Data Index: 8657476 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2527. Min Range: -7.2527
Max Act: 7.1589. Min Act: -0.1700
Data Index: 2583729 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2527. Min Range: -7.2527
Max Act: 7.1277. Min Act: -0.1700
Data Index: 6959135 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2527. Min Range: -7.2527
Max Act: 7.0964. Min Act: -0.1700
Data Index: 2444887 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2527. Min Range: -7.2527
Max Act: 7.0652. Min Act: -0.1700
Data Index: 6383617 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.9402. Min Act: -0.1700
Data Index: 8532382 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.8777. Min Act: -0.1700
Data Index: 1076924 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.8777. Min Act: -0.1700
Data Index: 6959134 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.8152. Min Act: -0.1700
Data Index: 3237565 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.8152. Min Act: -0.1700
Data Index: 6725810 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.8152. Min Act: -0.1700
Data Index: 1237131 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.8152. Min Act: -0.1700
Data Index: 3506991 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.7839. Min Act: -0.1700
Data Index: 623778 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.7839. Min Act: -0.1700
Data Index: 1662097 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.7214. Min Act: -0.1700
Data Index: 3594763 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.7214. Min Act: -0.1700
Data Index: 5056476 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.7527. Min Act: -0.1700
Data Index: 149334 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2527. Min Range: -7.2527
Max Act: 6.7527. Min Act: -0.1700
Data Index: 4325208 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19