Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2497 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.7784. Min Act: -0.0639
Data Index: 2373815 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.7145. Min Act: -0.0698
Data Index: 3939655 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.6505. Min Act: -0.0916
Data Index: 7828354 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.6825. Min Act: -0.0155
Data Index: 4621410 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.6505. Min Act: -0.1208
Data Index: 3578598 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.6505. Min Act: -0.0104
Data Index: 5913646 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.5862. Min Act: -0.0755
Data Index: 3750268 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.6183. Min Act: -0.0327
Data Index: 512450 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.6183. Min Act: -0.0089
Data Index: 1452633 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.6183. Min Act: -0.0639
Data Index: 412954 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.6183. Min Act: -0.0712
Data Index: 3333665 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.5862. Min Act: -0.0783
Data Index: 2667998 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.5862. Min Act: -0.0130
Data Index: 5597937 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.5539. Min Act: -0.1318
Data Index: 8818025 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.5862. Min Act: -0.1168
Data Index: 2959361 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.5539. Min Act: -0.0278
Data Index: 5747342 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.5216. Min Act: -0.0865
Data Index: 4999724 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.5216. Min Act: -0.0279
Data Index: 2418354 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.4892. Min Act: -0.0402
Data Index: 1532518 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7784. Min Range: -2.7784
Max Act: 2.5216. Min Act: -0.1286
Data Index: 6430933 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19