Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 371 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.5652. Min Act: -0.1700
Data Index: 4068544 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.5182. Min Act: -0.1700
Data Index: 4867954 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.5026. Min Act: -0.1700
Data Index: 7264245 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.4399. Min Act: -0.1700
Data Index: 7110007 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.4242. Min Act: -0.1700
Data Index: 400511 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.4086. Min Act: -0.1700
Data Index: 7896740 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.4086. Min Act: -0.1700
Data Index: 7783323 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.4086. Min Act: -0.1700
Data Index: 6654565 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3929. Min Act: -0.1700
Data Index: 4345354 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3772. Min Act: -0.1700
Data Index: 7264244 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3929. Min Act: -0.1700
Data Index: 8289919 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3615. Min Act: -0.1700
Data Index: 1183788 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3615. Min Act: -0.1700
Data Index: 3683632 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3615. Min Act: -0.1700
Data Index: 5960621 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3772. Min Act: -0.1700
Data Index: 7157990 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3301. Min Act: -0.1700
Data Index: 2131913 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3458. Min Act: -0.1700
Data Index: 6030602 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3615. Min Act: -0.1700
Data Index: 116932 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3458. Min Act: -0.1700
Data Index: 5249081 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3301. Min Act: -0.1700
Data Index: 6301634 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19