Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.9835. Min Act: -0.1700
Data Index: 7179538 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.7960. Min Act: -0.1700
Data Index: 3952446 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.7960. Min Act: -0.1700
Data Index: 4099859 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.6710. Min Act: -0.1700
Data Index: 7676655 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.6710. Min Act: -0.1700
Data Index: 7332567 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.6397. Min Act: -0.1700
Data Index: 1134288 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.6397. Min Act: -0.1700
Data Index: 751871 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.6085. Min Act: -0.1700
Data Index: 5425332 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.6085. Min Act: -0.1700
Data Index: 5085425 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.6085. Min Act: -0.1700
Data Index: 4373436 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.5772. Min Act: -0.1700
Data Index: 492856 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.5772. Min Act: -0.1700
Data Index: 4032327 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.5460. Min Act: -0.1700
Data Index: 3297883 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.5147. Min Act: -0.1700
Data Index: 7694679 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.5147. Min Act: -0.1700
Data Index: 7676656 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.5147. Min Act: -0.1700
Data Index: 8124694 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.5147. Min Act: -0.1700
Data Index: 1016132 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4522. Min Act: -0.1700
Data Index: 6438614 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4835. Min Act: -0.1700
Data Index: 3849897 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4835. Min Act: -0.1700
Data Index: 8376282 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19