Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3531 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.7809. Min Act: -0.1700
Data Index: 3761158 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.6559. Min Act: -0.1700
Data Index: 6430131 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.4684. Min Act: -0.1700
Data Index: 8277857 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.4371. Min Act: -0.1700
Data Index: 82129 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.2809. Min Act: -0.1700
Data Index: 2561695 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.1871. Min Act: -0.1700
Data Index: 1174972 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.1559. Min Act: -0.1700
Data Index: 3211240 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.1559. Min Act: -0.1700
Data Index: 119551 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.0934. Min Act: -0.1700
Data Index: 4584919 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.0934. Min Act: -0.1700
Data Index: 8802326 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.0621. Min Act: -0.1700
Data Index: 2227094 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.0621. Min Act: -0.1700
Data Index: 5690997 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.0621. Min Act: -0.1700
Data Index: 5366686 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.0309. Min Act: -0.1700
Data Index: 4819331 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7809. Min Range: -6.7809
Max Act: 6.0309. Min Act: -0.1700
Data Index: 6986772 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7809. Min Range: -6.7809
Max Act: 5.9996. Min Act: -0.1700
Data Index: 213503 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7809. Min Range: -6.7809
Max Act: 5.9996. Min Act: -0.1700
Data Index: 722302 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7809. Min Range: -6.7809
Max Act: 5.9684. Min Act: -0.1700
Data Index: 8447070 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7809. Min Range: -6.7809
Max Act: 5.9371. Min Act: -0.1700
Data Index: 8401316 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7809. Min Range: -6.7809
Max Act: 5.9684. Min Act: -0.1700
Data Index: 7532393 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19