Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.8769. Min Act: -0.1700
Data Index: 11367 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.8769. Min Act: -0.1700
Data Index: 7837545 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.6269. Min Act: -0.1700
Data Index: 378075 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.6269. Min Act: -0.1700
Data Index: 5392892 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.5644. Min Act: -0.1700
Data Index: 378056 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.5332. Min Act: -0.1700
Data Index: 2334836 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.5019. Min Act: -0.1700
Data Index: 161609 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.3769. Min Act: -0.1700
Data Index: 8626392 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.3457. Min Act: -0.1700
Data Index: 5341643 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.3769. Min Act: -0.1697
Data Index: 7394406 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.3457. Min Act: -0.1700
Data Index: 3169341 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.3144. Min Act: -0.1700
Data Index: 5188763 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.2519. Min Act: -0.1700
Data Index: 2305305 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.2207. Min Act: -0.1700
Data Index: 2064166 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.2519. Min Act: -0.1698
Data Index: 378074 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.2519. Min Act: -0.1700
Data Index: 4041545 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.2207. Min Act: -0.1700
Data Index: 6470391 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.2207. Min Act: -0.1699
Data Index: 378064 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.2207. Min Act: -0.1700
Data Index: 2201731 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8769. Min Range: -7.8769
Max Act: 7.1894. Min Act: -0.1700
Data Index: 141454 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19