Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2554 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0121. Min Range: -8.0121
Max Act: 8.0121. Min Act: -0.1700
Data Index: 8666775 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.7621. Min Act: -0.1700
Data Index: 3793000 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.7621. Min Act: -0.1700
Data Index: 5590630 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.6996. Min Act: -0.1700
Data Index: 5902038 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.5746. Min Act: -0.1700
Data Index: 7778359 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.5121. Min Act: -0.1700
Data Index: 1425436 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.5121. Min Act: -0.1700
Data Index: 2796433 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.4809. Min Act: -0.1700
Data Index: 1608062 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.4809. Min Act: -0.1700
Data Index: 551455 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.4496. Min Act: -0.1700
Data Index: 2105354 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.4184. Min Act: -0.1700
Data Index: 4885197 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.3246. Min Act: -0.1700
Data Index: 7322979 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.3246. Min Act: -0.1700
Data Index: 1293255 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.3559. Min Act: -0.1700
Data Index: 8471422 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.3246. Min Act: -0.1700
Data Index: 1377087 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.3246. Min Act: -0.1700
Data Index: 3275445 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.2934. Min Act: -0.1700
Data Index: 8123594 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.2934. Min Act: -0.1700
Data Index: 1073572 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.2621. Min Act: -0.1700
Data Index: 3062371 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0121. Min Range: -8.0121
Max Act: 7.2309. Min Act: -0.1700
Data Index: 1897245 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19