Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1829 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.6338. Min Act: -0.1700
Data Index: 8663882 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.5088. Min Act: -0.1700
Data Index: 4010858 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.4463. Min Act: -0.1700
Data Index: 6960570 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.3526. Min Act: -0.1700
Data Index: 7613196 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.3526. Min Act: -0.1700
Data Index: 5540181 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.3526. Min Act: -0.1700
Data Index: 6515169 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.3213. Min Act: -0.1700
Data Index: 4569523 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.3526. Min Act: -0.1700
Data Index: 4217596 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2901. Min Act: -0.1700
Data Index: 201033 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2588. Min Act: -0.1700
Data Index: 2619977 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2901. Min Act: -0.1700
Data Index: 731666 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2901. Min Act: -0.1700
Data Index: 2146317 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2588. Min Act: -0.1700
Data Index: 6236745 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2588. Min Act: -0.1700
Data Index: 8505754 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2588. Min Act: -0.1700
Data Index: 2571601 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2588. Min Act: -0.1700
Data Index: 3551017 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2588. Min Act: -0.1700
Data Index: 2267691 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2276. Min Act: -0.1700
Data Index: 6495179 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2276. Min Act: -0.1700
Data Index: 7857677 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6338. Min Range: -5.6338
Max Act: 5.2276. Min Act: -0.1700
Data Index: 1359350 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19