Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 748 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.7326. Min Act: -0.1700
Data Index: 7913951 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.6701. Min Act: -0.1700
Data Index: 2087120 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.6701. Min Act: -0.1699
Data Index: 6851112 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.6389. Min Act: -0.1699
Data Index: 4866961 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.6389. Min Act: -0.1700
Data Index: 8115095 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.6076. Min Act: -0.1697
Data Index: 8701429 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5764. Min Act: -0.1700
Data Index: 224985 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.6076. Min Act: -0.1700
Data Index: 2267070 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5764. Min Act: -0.1700
Data Index: 778336 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5451. Min Act: -0.1700
Data Index: 5370658 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5764. Min Act: -0.1700
Data Index: 3370734 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5451. Min Act: -0.1700
Data Index: 994813 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5451. Min Act: -0.1699
Data Index: 778332 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5451. Min Act: -0.1700
Data Index: 8640148 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5764. Min Act: -0.1700
Data Index: 7582228 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5451. Min Act: -0.1700
Data Index: 8299614 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5451. Min Act: -0.1700
Data Index: 1085720 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5451. Min Act: -0.1696
Data Index: 7484884 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5451. Min Act: -0.1700
Data Index: 7154286 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7326. Min Range: -5.7326
Max Act: 5.5139. Min Act: -0.1700
Data Index: 4896145 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19