Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2713 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.9816. Min Act: -0.1700
Data Index: 431726 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.8879. Min Act: -0.1700
Data Index: 6912345 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.7629. Min Act: -0.1700
Data Index: 6043850 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.7004. Min Act: -0.1700
Data Index: 2698118 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.6379. Min Act: -0.1700
Data Index: 4715688 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.5441. Min Act: -0.1700
Data Index: 2669818 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.5129. Min Act: -0.1700
Data Index: 1269608 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.4816. Min Act: -0.1700
Data Index: 2376178 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.4191. Min Act: -0.1700
Data Index: 1544 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.4191. Min Act: -0.1700
Data Index: 6720435 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.3879. Min Act: -0.1700
Data Index: 1428536 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.3879. Min Act: -0.1700
Data Index: 5366562 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.3566. Min Act: -0.1700
Data Index: 7033389 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.2941. Min Act: -0.1700
Data Index: 4518449 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.3254. Min Act: -0.1700
Data Index: 3636360 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.2941. Min Act: -0.1700
Data Index: 4794099 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.2941. Min Act: -0.1700
Data Index: 7798574 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.2941. Min Act: -0.1700
Data Index: 1140831 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.2629. Min Act: -0.1700
Data Index: 3016413 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9816. Min Range: -7.9816
Max Act: 7.2629. Min Act: -0.1700
Data Index: 3220991 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19