Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6392 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2403. Min Range: -4.2403
Max Act: 4.2403. Min Act: -0.1700
Data Index: 6241460 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2403. Min Range: -4.2403
Max Act: 4.2091. Min Act: -0.1700
Data Index: 8335320 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2403. Min Range: -4.2403
Max Act: 4.1778. Min Act: -0.1700
Data Index: 6580861 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2403. Min Range: -4.2403
Max Act: 4.1466. Min Act: -0.1700
Data Index: 768097 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2403. Min Range: -4.2403
Max Act: 4.1153. Min Act: -0.1700
Data Index: 5023844 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2403. Min Range: -4.2403
Max Act: 4.1153. Min Act: -0.1700
Data Index: 5011551 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2403. Min Range: -4.2403
Max Act: 4.1153. Min Act: -0.1700
Data Index: 2462557 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2403. Min Range: -4.2403
Max Act: 4.0215. Min Act: -0.1700
Data Index: 7527080 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2403. Min Range: -4.2403
Max Act: 4.0215. Min Act: -0.1700
Data Index: 7472204 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2403. Min Range: -4.2403
Max Act: 3.9590. Min Act: -0.1700
Data Index: 8405703 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2403. Min Range: -4.2403
Max Act: 3.9590. Min Act: -0.1700
Data Index: 4649390 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2403. Min Range: -4.2403
Max Act: 3.9277. Min Act: -0.1700
Data Index: 5788354 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2403. Min Range: -4.2403
Max Act: 3.9277. Min Act: -0.1700
Data Index: 2687831 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2403. Min Range: -4.2403
Max Act: 3.9277. Min Act: -0.1700
Data Index: 7345966 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2403. Min Range: -4.2403
Max Act: 3.9277. Min Act: -0.1700
Data Index: 3499759 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2403. Min Range: -4.2403
Max Act: 3.8965. Min Act: -0.1700
Data Index: 4996744 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2403. Min Range: -4.2403
Max Act: 3.8965. Min Act: -0.1700
Data Index: 1796753 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2403. Min Range: -4.2403
Max Act: 3.8965. Min Act: -0.1700
Data Index: 6745266 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2403. Min Range: -4.2403
Max Act: 3.8965. Min Act: -0.1700
Data Index: 1600172 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2403. Min Range: -4.2403
Max Act: 3.8965. Min Act: -0.1700
Data Index: 1330640 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19