Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 561 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.6274. Min Act: -0.1700
Data Index: 2289297 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.6274. Min Act: -0.1700
Data Index: 5830624 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5961. Min Act: -0.1700
Data Index: 8324843 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5961. Min Act: -0.1700
Data Index: 2664467 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5961. Min Act: -0.1700
Data Index: 5604785 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5961. Min Act: -0.1700
Data Index: 3648907 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5649. Min Act: -0.1700
Data Index: 7856164 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5649. Min Act: -0.1700
Data Index: 50156 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5649. Min Act: -0.1700
Data Index: 1532679 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5649. Min Act: -0.1700
Data Index: 1934045 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5649. Min Act: -0.1700
Data Index: 6571397 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5649. Min Act: -0.1700
Data Index: 457291 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5649. Min Act: -0.1700
Data Index: 1156673 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5649. Min Act: -0.1700
Data Index: 3233681 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5336. Min Act: -0.1700
Data Index: 934390 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5336. Min Act: -0.1700
Data Index: 5734706 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5336. Min Act: -0.1700
Data Index: 1829147 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5024. Min Act: -0.1700
Data Index: 4127637 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5336. Min Act: -0.1700
Data Index: 5343199 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6274. Min Range: -5.6274
Max Act: 5.5649. Min Act: -0.1700
Data Index: 6890190 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19