Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1984 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.6810. Min Act: -0.1700
Data Index: 3998841 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.6810. Min Act: -0.1700
Data Index: 7829047 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.5715. Min Act: -0.1700
Data Index: 5530520 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.5245. Min Act: -0.1700
Data Index: 7025573 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.5088. Min Act: -0.1700
Data Index: 2211027 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4775. Min Act: -0.1700
Data Index: 8324436 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4462. Min Act: -0.1700
Data Index: 6201145 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4619. Min Act: -0.1700
Data Index: 181942 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4619. Min Act: -0.1700
Data Index: 6742471 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4462. Min Act: -0.1700
Data Index: 3441310 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4462. Min Act: -0.1700
Data Index: 1708463 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4305. Min Act: -0.1700
Data Index: 8654765 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4148. Min Act: -0.1700
Data Index: 1467186 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4148. Min Act: -0.1700
Data Index: 3172281 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4148. Min Act: -0.1700
Data Index: 8413111 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3992. Min Act: -0.1700
Data Index: 4925820 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4148. Min Act: -0.1700
Data Index: 6378895 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3835. Min Act: -0.1700
Data Index: 3253613 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3835. Min Act: -0.1700
Data Index: 1114313 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3835. Min Act: -0.1700
Data Index: 7236745 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19