Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2902 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.2519. Min Act: -0.1700
Data Index: 6333012 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.1582. Min Act: -0.1700
Data Index: 989410 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2519. Min Range: -8.2519
Max Act: 8.0644. Min Act: -0.1700
Data Index: 1052397 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.9707. Min Act: -0.1700
Data Index: 6035591 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.9394. Min Act: -0.1700
Data Index: 3258413 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.9082. Min Act: -0.1700
Data Index: 8656950 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.9082. Min Act: -0.1700
Data Index: 1292792 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.9082. Min Act: -0.1700
Data Index: 4489488 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.8457. Min Act: -0.1700
Data Index: 1345449 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.8457. Min Act: -0.1700
Data Index: 2186510 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.8144. Min Act: -0.1700
Data Index: 6112645 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.8144. Min Act: -0.1700
Data Index: 6633748 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.7519. Min Act: -0.1700
Data Index: 1699920 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.7832. Min Act: -0.1700
Data Index: 3113455 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.7207. Min Act: -0.1700
Data Index: 7300110 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.7207. Min Act: -0.1700
Data Index: 7717162 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.7207. Min Act: -0.1700
Data Index: 5529464 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.7207. Min Act: -0.1700
Data Index: 2095203 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.6894. Min Act: -0.1700
Data Index: 2067920 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2519. Min Range: -8.2519
Max Act: 7.6894. Min Act: -0.1700
Data Index: 1140437 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19