Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3343 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.5387. Min Act: -0.1700
Data Index: 6779843 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.5075. Min Act: -0.1700
Data Index: 6502544 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.4762. Min Act: -0.1700
Data Index: 7063859 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.4762. Min Act: -0.1700
Data Index: 2658341 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.4450. Min Act: -0.1700
Data Index: 2914303 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.4137. Min Act: -0.1700
Data Index: 6166250 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.3825. Min Act: -0.1700
Data Index: 648803 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.3825. Min Act: -0.1700
Data Index: 1859233 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.3200. Min Act: -0.1700
Data Index: 2202501 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.2887. Min Act: -0.1700
Data Index: 3772190 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.3512. Min Act: -0.1700
Data Index: 2212968 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.2887. Min Act: -0.1700
Data Index: 860980 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.2887. Min Act: -0.1700
Data Index: 5806455 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.2574. Min Act: -0.1700
Data Index: 5984115 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.2574. Min Act: -0.1700
Data Index: 5270251 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.2574. Min Act: -0.1700
Data Index: 3071408 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.2574. Min Act: -0.1700
Data Index: 7227969 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.2574. Min Act: -0.1700
Data Index: 2662050 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.2262. Min Act: -0.1700
Data Index: 677796 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5387. Min Range: -4.5387
Max Act: 4.2262. Min Act: -0.1700
Data Index: 2718025 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19