Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1546 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.7798. Min Act: -0.1700
Data Index: 2950934 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.6860. Min Act: -0.1700
Data Index: 1432703 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.6235. Min Act: -0.1700
Data Index: 526949 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.4985. Min Act: -0.1700
Data Index: 8124585 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.4673. Min Act: -0.1700
Data Index: 5658546 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.4673. Min Act: -0.1700
Data Index: 2826685 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.4360. Min Act: -0.1700
Data Index: 3588693 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.4360. Min Act: -0.1700
Data Index: 4917064 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.4048. Min Act: -0.1700
Data Index: 267757 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.3735. Min Act: -0.1700
Data Index: 440309 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.3423. Min Act: -0.1700
Data Index: 4076226 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.3423. Min Act: -0.1700
Data Index: 1317235 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.2798. Min Act: -0.1700
Data Index: 4847228 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.2798. Min Act: -0.1700
Data Index: 7236268 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.2485. Min Act: -0.1700
Data Index: 1000483 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.2173. Min Act: -0.1700
Data Index: 5360427 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.2173. Min Act: -0.1700
Data Index: 4660720 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.1860. Min Act: -0.1700
Data Index: 7645666 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.1860. Min Act: -0.1700
Data Index: 1864568 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7798. Min Range: -5.7798
Max Act: 5.1860. Min Act: -0.1700
Data Index: 5881759 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19