Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6359 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.9846. Min Act: -0.1700
Data Index: 1481969 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.8908. Min Act: -0.1700
Data Index: 4304843 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.8752. Min Act: -0.1700
Data Index: 2571587 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.8596. Min Act: -0.1700
Data Index: 8303281 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.8283. Min Act: -0.1700
Data Index: 4416392 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.8283. Min Act: -0.1700
Data Index: 2991454 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.8127. Min Act: -0.1700
Data Index: 5984787 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.7814. Min Act: -0.1700
Data Index: 1839618 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.8127. Min Act: -0.1700
Data Index: 1450403 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.7657. Min Act: -0.1700
Data Index: 582587 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.7814. Min Act: -0.1700
Data Index: 1503602 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.7814. Min Act: -0.1700
Data Index: 5109052 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.7657. Min Act: -0.1700
Data Index: 8793542 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.7345. Min Act: -0.1700
Data Index: 1561923 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.7188. Min Act: -0.1700
Data Index: 5436331 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.7188. Min Act: -0.1700
Data Index: 58064 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.7032. Min Act: -0.1700
Data Index: 6736335 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.7032. Min Act: -0.1700
Data Index: 7570769 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.7188. Min Act: -0.1700
Data Index: 2327415 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9846. Min Range: -3.9846
Max Act: 3.6875. Min Act: -0.1700
Data Index: 5149694 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19