Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2405 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1202. Min Range: -7.1202
Max Act: 7.1202. Min Act: -0.1700
Data Index: 7919645 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.9014. Min Act: -0.1700
Data Index: 6594341 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.6827. Min Act: -0.1700
Data Index: 788738 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.4639. Min Act: -0.1700
Data Index: 53997 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.4327. Min Act: -0.1700
Data Index: 4632656 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.3702. Min Act: -0.1700
Data Index: 6732282 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.3702. Min Act: -0.1700
Data Index: 3081292 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.3702. Min Act: -0.1700
Data Index: 3317857 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.3389. Min Act: -0.1700
Data Index: 8831739 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.3389. Min Act: -0.1700
Data Index: 1746826 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.3077. Min Act: -0.1700
Data Index: 1026441 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.3389. Min Act: -0.1700
Data Index: 1683347 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.3077. Min Act: -0.1700
Data Index: 6817131 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2764. Min Act: -0.1700
Data Index: 103128 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2764. Min Act: -0.1700
Data Index: 3185360 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2452. Min Act: -0.1700
Data Index: 3889583 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2452. Min Act: -0.1700
Data Index: 650691 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.2139. Min Act: -0.1700
Data Index: 2666443 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.1827. Min Act: -0.1700
Data Index: 4331756 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1202. Min Range: -7.1202
Max Act: 6.1827. Min Act: -0.1700
Data Index: 7518394 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19