Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0881. Min Range: -4.0881
Max Act: 4.0881. Min Act: -0.1700
Data Index: 6935906 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.9944. Min Act: -0.1700
Data Index: 1288642 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.9944. Min Act: -0.1700
Data Index: 1288646 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.9318. Min Act: -0.1700
Data Index: 1288647 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.9318. Min Act: -0.1700
Data Index: 1288644 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.8380. Min Act: -0.1700
Data Index: 6053258 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.8068. Min Act: -0.1700
Data Index: 1288641 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.8068. Min Act: -0.1700
Data Index: 1288639 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.8068. Min Act: -0.1700
Data Index: 1288638 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.7755. Min Act: -0.1700
Data Index: 8293690 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.7755. Min Act: -0.1700
Data Index: 4251137 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.7129. Min Act: -0.1700
Data Index: 8589695 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.7442. Min Act: -0.1700
Data Index: 4163630 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.7442. Min Act: -0.1700
Data Index: 3421770 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.7442. Min Act: -0.1700
Data Index: 1288648 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.7442. Min Act: -0.1700
Data Index: 4113705 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.7442. Min Act: -0.1700
Data Index: 1288640 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.7129. Min Act: -0.1700
Data Index: 2608882 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.7129. Min Act: -0.1700
Data Index: 6030669 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0881. Min Range: -4.0881
Max Act: 3.7129. Min Act: -0.1700
Data Index: 6121544 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19