Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5321 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.6899. Min Act: -0.1700
Data Index: 8304579 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.6274. Min Act: -0.1700
Data Index: 3430997 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.4712. Min Act: -0.1700
Data Index: 5302890 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.4712. Min Act: -0.1700
Data Index: 2408787 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.4399. Min Act: -0.1700
Data Index: 5930432 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.4087. Min Act: -0.1700
Data Index: 6401673 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.4087. Min Act: -0.1700
Data Index: 253886 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.3462. Min Act: -0.1700
Data Index: 5675673 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.3774. Min Act: -0.1700
Data Index: 1220438 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.3774. Min Act: -0.1700
Data Index: 7185534 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.3774. Min Act: -0.1700
Data Index: 230248 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.3462. Min Act: -0.1700
Data Index: 7324139 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.3774. Min Act: -0.1700
Data Index: 8224028 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.3462. Min Act: -0.1700
Data Index: 3585700 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.3462. Min Act: -0.1700
Data Index: 5592459 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.3149. Min Act: -0.1700
Data Index: 1368190 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.3149. Min Act: -0.1700
Data Index: 5930429 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.3149. Min Act: -0.1700
Data Index: 1368191 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.3149. Min Act: -0.1700
Data Index: 6217421 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6899. Min Range: -5.6899
Max Act: 5.2837. Min Act: -0.1700
Data Index: 4361487 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19