Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3717 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2297. Min Range: -7.2297
Max Act: 7.2297. Min Act: -0.1700
Data Index: 7373720 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2297. Min Range: -7.2297
Max Act: 7.0735. Min Act: -0.1700
Data Index: 863612 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2297. Min Range: -7.2297
Max Act: 7.0735. Min Act: -0.1700
Data Index: 6151183 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.9797. Min Act: -0.1700
Data Index: 269091 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.9485. Min Act: -0.1700
Data Index: 1237745 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.9172. Min Act: -0.1700
Data Index: 4774146 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.9172. Min Act: -0.1700
Data Index: 1058668 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.8547. Min Act: -0.1700
Data Index: 4509685 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.8860. Min Act: -0.1700
Data Index: 3052934 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.8235. Min Act: -0.1700
Data Index: 522019 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.8235. Min Act: -0.1700
Data Index: 7974268 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.8235. Min Act: -0.1700
Data Index: 5367275 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.7922. Min Act: -0.1700
Data Index: 7185288 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.8235. Min Act: -0.1700
Data Index: 1110868 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.7610. Min Act: -0.1700
Data Index: 6199552 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.7297. Min Act: -0.1700
Data Index: 514651 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.7297. Min Act: -0.1700
Data Index: 2016136 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.7297. Min Act: -0.1700
Data Index: 185500 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.6985. Min Act: -0.1700
Data Index: 6299074 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2297. Min Range: -7.2297
Max Act: 6.6985. Min Act: -0.1700
Data Index: 310548 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19