Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6051 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.5692. Min Act: -0.1700
Data Index: 3034450 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.4755. Min Act: -0.1700
Data Index: 3707370 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.4442. Min Act: -0.1700
Data Index: 2059411 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.2880. Min Act: -0.1700
Data Index: 5953288 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.2255. Min Act: -0.1700
Data Index: 815298 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.1630. Min Act: -0.1700
Data Index: 377284 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.1942. Min Act: -0.1700
Data Index: 7063029 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.1630. Min Act: -0.1700
Data Index: 8694907 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.1630. Min Act: -0.1700
Data Index: 8295372 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.1942. Min Act: -0.1700
Data Index: 1032529 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.1630. Min Act: -0.1700
Data Index: 6966956 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.1630. Min Act: -0.1700
Data Index: 5972770 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.1630. Min Act: -0.1700
Data Index: 3252376 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.1317. Min Act: -0.1700
Data Index: 6813211 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.1317. Min Act: -0.1700
Data Index: 532088 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.1317. Min Act: -0.1700
Data Index: 4442824 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.0692. Min Act: -0.1700
Data Index: 408470 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.0692. Min Act: -0.1700
Data Index: 3372944 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.0380. Min Act: -0.1700
Data Index: 3962803 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.0692. Min Act: -0.1700
Data Index: 2636058 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19