Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2502 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2088. Min Range: -3.2088
Max Act: 3.2088. Min Act: -0.1700
Data Index: 3044543 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2088. Min Range: -3.2088
Max Act: 3.1458. Min Act: -0.1700
Data Index: 5931006 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2088. Min Range: -3.2088
Max Act: 3.0986. Min Act: -0.1700
Data Index: 5615007 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9565. Min Act: -0.1700
Data Index: 6150578 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9248. Min Act: -0.1700
Data Index: 3405814 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8931. Min Act: -0.1700
Data Index: 1224024 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9089. Min Act: -0.1700
Data Index: 1856176 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8772. Min Act: -0.1700
Data Index: 1967384 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8931. Min Act: -0.1700
Data Index: 1799264 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8613. Min Act: -0.1700
Data Index: 5783047 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8454. Min Act: -0.1700
Data Index: 2293985 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8295. Min Act: -0.1700
Data Index: 4417133 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8295. Min Act: -0.1700
Data Index: 8654583 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8136. Min Act: -0.1700
Data Index: 2256154 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8136. Min Act: -0.1700
Data Index: 7611918 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.7977. Min Act: -0.1700
Data Index: 5922679 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8136. Min Act: -0.1700
Data Index: 4219896 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.7818. Min Act: -0.1700
Data Index: 616260 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.7977. Min Act: -0.1700
Data Index: 3316600 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.7818. Min Act: -0.1700
Data Index: 3654084 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19