Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3624 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1208. Min Range: -5.1208
Max Act: 5.1208. Min Act: -0.1700
Data Index: 2998741 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1208. Min Range: -5.1208
Max Act: 5.1208. Min Act: -0.1700
Data Index: 924999 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.9958. Min Act: -0.1700
Data Index: 2732555 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.9645. Min Act: -0.1700
Data Index: 4707662 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.9020. Min Act: -0.1700
Data Index: 6888715 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.9020. Min Act: -0.1700
Data Index: 7824439 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.9020. Min Act: -0.1700
Data Index: 5164027 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.8395. Min Act: -0.1700
Data Index: 4052134 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.8395. Min Act: -0.1700
Data Index: 8267880 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.8083. Min Act: -0.1700
Data Index: 3838079 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7770. Min Act: -0.1700
Data Index: 5505010 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7770. Min Act: -0.1700
Data Index: 8040625 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7770. Min Act: -0.1700
Data Index: 3747334 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7770. Min Act: -0.1700
Data Index: 5810622 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7458. Min Act: -0.1700
Data Index: 3750931 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7458. Min Act: -0.1700
Data Index: 418903 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7458. Min Act: -0.1700
Data Index: 2639472 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7458. Min Act: -0.1700
Data Index: 599423 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7458. Min Act: -0.1700
Data Index: 5963864 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1208. Min Range: -5.1208
Max Act: 4.7145. Min Act: -0.1700
Data Index: 5403414 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19