Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4514 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3643. Min Range: -7.3643
Max Act: 7.3643. Min Act: -0.1700
Data Index: 8022265 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3643. Min Range: -7.3643
Max Act: 7.0206. Min Act: -0.1700
Data Index: 3178152 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.8018. Min Act: -0.1700
Data Index: 3111324 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.8018. Min Act: -0.1700
Data Index: 4618287 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.7706. Min Act: -0.1700
Data Index: 5964351 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.7706. Min Act: -0.1700
Data Index: 8461059 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.7393. Min Act: -0.1700
Data Index: 8737173 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.7393. Min Act: -0.1700
Data Index: 4415043 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.6768. Min Act: -0.1700
Data Index: 5045036 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.6456. Min Act: -0.1700
Data Index: 1345509 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.5831. Min Act: -0.1700
Data Index: 5920379 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.5831. Min Act: -0.1700
Data Index: 3774019 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.5831. Min Act: -0.1700
Data Index: 8664072 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.5518. Min Act: -0.1700
Data Index: 706020 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.5518. Min Act: -0.1700
Data Index: 4635991 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.5206. Min Act: -0.1700
Data Index: 6986178 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.5206. Min Act: -0.1700
Data Index: 2932798 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.4893. Min Act: -0.1700
Data Index: 1592883 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.4893. Min Act: -0.1700
Data Index: 4895155 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3643. Min Range: -7.3643
Max Act: 6.4581. Min Act: -0.1700
Data Index: 843804 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19