Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.3125. Min Act: -0.1700
Data Index: 7703820 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.2811. Min Act: -0.1700
Data Index: 6874685 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.2497. Min Act: -0.1700
Data Index: 7204456 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.1868. Min Act: -0.1700
Data Index: 2029002 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.1868. Min Act: -0.1700
Data Index: 5296630 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.1081. Min Act: -0.1700
Data Index: 2812897 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.1081. Min Act: -0.1700
Data Index: 2517392 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.0608. Min Act: -0.1700
Data Index: 7224282 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.0450. Min Act: -0.1700
Data Index: 3653397 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.0766. Min Act: -0.1700
Data Index: 2870141 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.0766. Min Act: -0.1700
Data Index: 6942228 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.0450. Min Act: -0.1700
Data Index: 4886545 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.0293. Min Act: -0.1700
Data Index: 6272494 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.0293. Min Act: -0.1700
Data Index: 7254688 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3125. Min Range: -3.3125
Max Act: 3.0135. Min Act: -0.1700
Data Index: 507901 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3125. Min Range: -3.3125
Max Act: 2.9977. Min Act: -0.1700
Data Index: 6774090 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3125. Min Range: -3.3125
Max Act: 2.9819. Min Act: -0.1700
Data Index: 3551244 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3125. Min Range: -3.3125
Max Act: 2.9977. Min Act: -0.1700
Data Index: 2361933 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3125. Min Range: -3.3125
Max Act: 2.9977. Min Act: -0.1700
Data Index: 3528329 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3125. Min Range: -3.3125
Max Act: 2.9977. Min Act: -0.1700
Data Index: 3932521 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19