Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3997 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.8203. Min Act: -0.1700
Data Index: 5908784 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.4453. Min Act: -0.1700
Data Index: 6588069 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.3516. Min Act: -0.1700
Data Index: 6900600 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.2891. Min Act: -0.1700
Data Index: 2412325 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.2578. Min Act: -0.1700
Data Index: 7685102 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.1953. Min Act: -0.1700
Data Index: 8072678 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.1328. Min Act: -0.1700
Data Index: 6342020 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.1016. Min Act: -0.1700
Data Index: 4449310 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.1016. Min Act: -0.1700
Data Index: 745109 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.1328. Min Act: -0.1700
Data Index: 4389714 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.1016. Min Act: -0.1700
Data Index: 4642352 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.1016. Min Act: -0.1700
Data Index: 4234857 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.1016. Min Act: -0.1700
Data Index: 3000848 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.0078. Min Act: -0.1700
Data Index: 4720989 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.0391. Min Act: -0.1700
Data Index: 3106496 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.0391. Min Act: -0.1700
Data Index: 1192323 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.0391. Min Act: -0.1700
Data Index: 3857505 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.0078. Min Act: -0.1700
Data Index: 3683187 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.0391. Min Act: -0.1700
Data Index: 4886824 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8203. Min Range: -6.8203
Max Act: 6.0391. Min Act: -0.1700
Data Index: 5593630 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19