Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3130 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.3210. Min Act: -0.1700
Data Index: 5315393 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.2273. Min Act: -0.1699
Data Index: 6205447 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.1335. Min Act: -0.1700
Data Index: 8237452 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.1335. Min Act: -0.1700
Data Index: 602490 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.1023. Min Act: -0.1698
Data Index: 6572599 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.0710. Min Act: -0.1700
Data Index: 8085043 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.1023. Min Act: -0.1700
Data Index: 412575 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.0710. Min Act: -0.1700
Data Index: 34733 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.0398. Min Act: -0.1700
Data Index: 2047861 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.0398. Min Act: -0.1700
Data Index: 1526429 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.0398. Min Act: -0.1700
Data Index: 6670011 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.0085. Min Act: -0.1700
Data Index: 1959473 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3210. Min Range: -6.3210
Max Act: 5.9773. Min Act: -0.1700
Data Index: 8379237 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3210. Min Range: -6.3210
Max Act: 5.9773. Min Act: -0.1700
Data Index: 8430532 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3210. Min Range: -6.3210
Max Act: 5.9773. Min Act: -0.1700
Data Index: 2047860 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3210. Min Range: -6.3210
Max Act: 6.0085. Min Act: -0.1700
Data Index: 1038805 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3210. Min Range: -6.3210
Max Act: 5.9460. Min Act: -0.1700
Data Index: 703971 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3210. Min Range: -6.3210
Max Act: 5.9148. Min Act: -0.1700
Data Index: 3721889 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3210. Min Range: -6.3210
Max Act: 5.9148. Min Act: -0.1700
Data Index: 1733593 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3210. Min Range: -6.3210
Max Act: 5.8835. Min Act: -0.1700
Data Index: 5991791 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19