Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5258 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.7116. Min Act: -0.1700
Data Index: 6320495 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.3991. Min Act: -0.1700
Data Index: 5468836 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.3366. Min Act: -0.1700
Data Index: 7798926 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.2741. Min Act: -0.1700
Data Index: 5113144 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.2741. Min Act: -0.1700
Data Index: 1826939 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.1491. Min Act: -0.1700
Data Index: 6328044 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.1491. Min Act: -0.1700
Data Index: 7119488 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.0241. Min Act: -0.1700
Data Index: 5420291 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.8991. Min Act: -0.1700
Data Index: 1120263 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.8991. Min Act: -0.1700
Data Index: 4418658 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.8991. Min Act: -0.1700
Data Index: 6983546 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.8366. Min Act: -0.1700
Data Index: 2613334 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.8991. Min Act: -0.1700
Data Index: 8621550 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.7741. Min Act: -0.1700
Data Index: 2329586 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.7741. Min Act: -0.1700
Data Index: 6226542 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.7116. Min Act: -0.1700
Data Index: 3940189 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.7116. Min Act: -0.1700
Data Index: 5609458 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.7116. Min Act: -0.1700
Data Index: 3575592 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.7116. Min Act: -0.1700
Data Index: 3340310 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.7116. Min Act: -0.1700
Data Index: 7067758 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19