Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5793 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0227. Min Range: -7.0227
Max Act: 7.0227. Min Act: -0.1700
Data Index: 8017268 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0227. Min Range: -7.0227
Max Act: 6.4914. Min Act: -0.1700
Data Index: 8017269 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0227. Min Range: -7.0227
Max Act: 6.1477. Min Act: -0.1700
Data Index: 8017277 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0227. Min Range: -7.0227
Max Act: 6.0539. Min Act: -0.1700
Data Index: 6097254 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0227. Min Range: -7.0227
Max Act: 6.0227. Min Act: -0.1700
Data Index: 8017278 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.9602. Min Act: -0.1700
Data Index: 3585498 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.9289. Min Act: -0.1700
Data Index: 3134383 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.8977. Min Act: -0.1700
Data Index: 2130444 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.8664. Min Act: -0.1700
Data Index: 6369983 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.8352. Min Act: -0.1700
Data Index: 1214493 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.8664. Min Act: -0.1700
Data Index: 3585491 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.8664. Min Act: -0.1700
Data Index: 4389923 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.8352. Min Act: -0.1700
Data Index: 6143074 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.8352. Min Act: -0.1700
Data Index: 7561582 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.8352. Min Act: -0.1700
Data Index: 3134379 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.8039. Min Act: -0.1700
Data Index: 3585501 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.8039. Min Act: -0.1700
Data Index: 8017267 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.7727. Min Act: -0.1700
Data Index: 7814027 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.8039. Min Act: -0.1700
Data Index: 5769718 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0227. Min Range: -7.0227
Max Act: 5.7727. Min Act: -0.1700
Data Index: 249281 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19