Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2167 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1414. Min Range: -9.1414
Max Act: 9.1414. Min Act: -0.1700
Data Index: 3641310 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.4539. Min Act: -0.1700
Data Index: 3641308 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.3914. Min Act: -0.1700
Data Index: 7080516 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.3914. Min Act: -0.1700
Data Index: 3464169 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.2664. Min Act: -0.1700
Data Index: 8736140 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.2664. Min Act: -0.1700
Data Index: 1464396 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.2664. Min Act: -0.1700
Data Index: 5817777 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.2039. Min Act: -0.1700
Data Index: 498877 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.2039. Min Act: -0.1700
Data Index: 3348899 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.2039. Min Act: -0.1700
Data Index: 2018812 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.1414. Min Act: -0.1700
Data Index: 2430322 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.1414. Min Act: -0.1700
Data Index: 6841869 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.0789. Min Act: -0.1700
Data Index: 7811365 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.0789. Min Act: -0.1700
Data Index: 6091283 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.0789. Min Act: -0.1700
Data Index: 4144669 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.0476. Min Act: -0.1700
Data Index: 1435756 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.0164. Min Act: -0.1700
Data Index: 3690420 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.0476. Min Act: -0.1700
Data Index: 2135176 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1414. Min Range: -9.1414
Max Act: 8.0164. Min Act: -0.1700
Data Index: 1646581 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1414. Min Range: -9.1414
Max Act: 7.9539. Min Act: -0.1700
Data Index: 109859 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19