Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4367 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.7283. Min Act: -0.1700
Data Index: 3130512 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.5720. Min Act: -0.1700
Data Index: 1340344 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.5408. Min Act: -0.1700
Data Index: 2692636 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.5408. Min Act: -0.1700
Data Index: 5874114 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.3845. Min Act: -0.1700
Data Index: 1829469 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.3845. Min Act: -0.1700
Data Index: 7273949 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.3220. Min Act: -0.1700
Data Index: 3238175 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.2908. Min Act: -0.1700
Data Index: 5838451 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.3220. Min Act: -0.1700
Data Index: 2916841 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.2595. Min Act: -0.1700
Data Index: 3644043 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.3845. Min Act: -0.1700
Data Index: 8180748 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.2283. Min Act: -0.1700
Data Index: 2894727 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.2283. Min Act: -0.1700
Data Index: 7846608 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.1970. Min Act: -0.1700
Data Index: 133832 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.1970. Min Act: -0.1700
Data Index: 51612 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.1970. Min Act: -0.1700
Data Index: 7753140 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.2283. Min Act: -0.1700
Data Index: 3345941 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.2283. Min Act: -0.1700
Data Index: 6339419 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.1345. Min Act: -0.1700
Data Index: 6111313 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7283. Min Range: -6.7283
Max Act: 6.1658. Min Act: -0.1700
Data Index: 5624628 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19