Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 246 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0021. Min Range: -8.0021
Max Act: 8.0021. Min Act: -0.1700
Data Index: 796870 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.5333. Min Act: -0.1700
Data Index: 8130987 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.4396. Min Act: -0.1700
Data Index: 7143673 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.4083. Min Act: -0.1700
Data Index: 8739429 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.3146. Min Act: -0.1700
Data Index: 5099134 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.3146. Min Act: -0.1700
Data Index: 3052892 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.2521. Min Act: -0.1700
Data Index: 5539678 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.2833. Min Act: -0.1700
Data Index: 3135290 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.2521. Min Act: -0.1700
Data Index: 27279 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.2208. Min Act: -0.1700
Data Index: 6127515 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.1896. Min Act: -0.1700
Data Index: 796871 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.1583. Min Act: -0.1700
Data Index: 4137143 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.1271. Min Act: -0.1700
Data Index: 7881372 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.0646. Min Act: -0.1700
Data Index: 6057607 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.0958. Min Act: -0.1700
Data Index: 5234085 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.0958. Min Act: -0.1700
Data Index: 3691221 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.0646. Min Act: -0.1700
Data Index: 5974575 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.0646. Min Act: -0.1700
Data Index: 3957809 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.0333. Min Act: -0.1700
Data Index: 2871744 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0021. Min Range: -8.0021
Max Act: 7.0646. Min Act: -0.1700
Data Index: 2851626 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19