Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5686 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6744. Min Range: -7.6744
Max Act: 7.6744. Min Act: -0.1700
Data Index: 5187288 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6744. Min Range: -7.6744
Max Act: 7.4244. Min Act: -0.1700
Data Index: 4733237 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6744. Min Range: -7.6744
Max Act: 7.3619. Min Act: -0.1700
Data Index: 6629930 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6744. Min Range: -7.6744
Max Act: 7.3619. Min Act: -0.1700
Data Index: 299422 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6744. Min Range: -7.6744
Max Act: 7.3307. Min Act: -0.1700
Data Index: 6582994 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6744. Min Range: -7.6744
Max Act: 7.2994. Min Act: -0.1700
Data Index: 8036890 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6744. Min Range: -7.6744
Max Act: 7.2682. Min Act: -0.1700
Data Index: 7857681 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6744. Min Range: -7.6744
Max Act: 7.1744. Min Act: -0.1700
Data Index: 5412265 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6744. Min Range: -7.6744
Max Act: 7.1744. Min Act: -0.1700
Data Index: 631729 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6744. Min Range: -7.6744
Max Act: 7.1432. Min Act: -0.1700
Data Index: 2353453 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6744. Min Range: -7.6744
Max Act: 7.0182. Min Act: -0.1700
Data Index: 7369651 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6744. Min Range: -7.6744
Max Act: 6.9869. Min Act: -0.1700
Data Index: 1850179 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6744. Min Range: -7.6744
Max Act: 6.9869. Min Act: -0.1700
Data Index: 4033804 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6744. Min Range: -7.6744
Max Act: 6.9557. Min Act: -0.1700
Data Index: 7516572 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6744. Min Range: -7.6744
Max Act: 6.9557. Min Act: -0.1700
Data Index: 1255553 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6744. Min Range: -7.6744
Max Act: 6.9244. Min Act: -0.1700
Data Index: 4794029 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6744. Min Range: -7.6744
Max Act: 6.9557. Min Act: -0.1700
Data Index: 3787244 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6744. Min Range: -7.6744
Max Act: 6.9557. Min Act: -0.1700
Data Index: 6138662 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6744. Min Range: -7.6744
Max Act: 6.9244. Min Act: -0.1700
Data Index: 7586801 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6744. Min Range: -7.6744
Max Act: 6.9244. Min Act: -0.1700
Data Index: 2352253 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19