Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3655 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3347. Min Range: -8.3347
Max Act: 8.3347. Min Act: -0.1700
Data Index: 8825800 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.9597. Min Act: -0.1700
Data Index: 2888801 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.7410. Min Act: -0.1700
Data Index: 6550482 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.7722. Min Act: -0.1700
Data Index: 770899 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.7097. Min Act: -0.1700
Data Index: 5752587 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.4597. Min Act: -0.1700
Data Index: 5371933 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.4597. Min Act: -0.1700
Data Index: 6806701 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3972. Min Act: -0.1700
Data Index: 1900645 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3660. Min Act: -0.1700
Data Index: 596306 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3660. Min Act: -0.1700
Data Index: 6258568 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3035. Min Act: -0.1699
Data Index: 5670335 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3035. Min Act: -0.1700
Data Index: 1835926 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3347. Min Act: -0.1700
Data Index: 5891726 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3660. Min Act: -0.1700
Data Index: 6692489 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3035. Min Act: -0.1698
Data Index: 365363 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3035. Min Act: -0.1700
Data Index: 3558472 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3035. Min Act: -0.1700
Data Index: 6337893 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3035. Min Act: -0.1700
Data Index: 7686717 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3035. Min Act: -0.1700
Data Index: 6687952 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3347. Min Range: -8.3347
Max Act: 7.3035. Min Act: -0.1700
Data Index: 1911194 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19