Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4654 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.6716. Min Act: -0.1700
Data Index: 7240122 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.6091. Min Act: -0.1700
Data Index: 4751022 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.6091. Min Act: -0.1700
Data Index: 3510290 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.6091. Min Act: -0.1700
Data Index: 2213266 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.5466. Min Act: -0.1700
Data Index: 8377699 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.5466. Min Act: -0.1700
Data Index: 1589217 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.5466. Min Act: -0.1700
Data Index: 7632633 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.5153. Min Act: -0.1700
Data Index: 66955 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.5153. Min Act: -0.1700
Data Index: 7344310 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.4841. Min Act: -0.1700
Data Index: 5511471 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.4841. Min Act: -0.1700
Data Index: 2178415 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.4841. Min Act: -0.1700
Data Index: 8008139 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.4216. Min Act: -0.1700
Data Index: 1775468 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.4528. Min Act: -0.1700
Data Index: 6885383 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.4528. Min Act: -0.1700
Data Index: 5526189 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.4216. Min Act: -0.1700
Data Index: 6607809 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.4216. Min Act: -0.1700
Data Index: 5985245 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.3903. Min Act: -0.1700
Data Index: 7160037 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.3903. Min Act: -0.1700
Data Index: 5781213 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6716. Min Range: -4.6716
Max Act: 4.3903. Min Act: -0.1700
Data Index: 4220064 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19