Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6365 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.9712. Min Act: -0.1700
Data Index: 7605127 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.8462. Min Act: -0.1700
Data Index: 488581 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.7837. Min Act: -0.1700
Data Index: 6574285 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.7837. Min Act: -0.1700
Data Index: 2972200 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.7212. Min Act: -0.1700
Data Index: 594010 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.6587. Min Act: -0.1700
Data Index: 4620287 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.5962. Min Act: -0.1700
Data Index: 314499 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.5962. Min Act: -0.1700
Data Index: 7458600 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.5337. Min Act: -0.1700
Data Index: 3083554 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.5962. Min Act: -0.1700
Data Index: 2450557 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.5337. Min Act: -0.1700
Data Index: 1641748 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.4087. Min Act: -0.1700
Data Index: 8540966 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.4087. Min Act: -0.1700
Data Index: 5955534 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.4087. Min Act: -0.1700
Data Index: 897535 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.4087. Min Act: -0.1700
Data Index: 1326591 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.4087. Min Act: -0.1700
Data Index: 2490048 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.3462. Min Act: -0.1700
Data Index: 2867187 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.3462. Min Act: -0.1700
Data Index: 4592847 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.3462. Min Act: -0.1700
Data Index: 4183928 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9712. Min Range: -9.9712
Max Act: 9.3462. Min Act: -0.1700
Data Index: 260471 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19