Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0395. Min Range: -8.0395
Max Act: 8.0395. Min Act: -0.1700
Data Index: 516566 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.8520. Min Act: -0.1700
Data Index: 389119 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.7895. Min Act: -0.1700
Data Index: 4912455 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.5083. Min Act: -0.1700
Data Index: 5885039 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.3833. Min Act: -0.1700
Data Index: 411535 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.3833. Min Act: -0.1700
Data Index: 2886483 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.3520. Min Act: -0.1700
Data Index: 4418623 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.3833. Min Act: -0.1700
Data Index: 7706718 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.3520. Min Act: -0.1700
Data Index: 7092452 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.3208. Min Act: -0.1700
Data Index: 115715 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.3208. Min Act: -0.1700
Data Index: 6279718 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.2895. Min Act: -0.1700
Data Index: 5185973 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.2583. Min Act: -0.1700
Data Index: 1796886 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.2583. Min Act: -0.1700
Data Index: 4269522 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.2895. Min Act: -0.1700
Data Index: 8828506 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.2270. Min Act: -0.1700
Data Index: 4627518 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.1645. Min Act: -0.1700
Data Index: 856514 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.1645. Min Act: -0.1700
Data Index: 603059 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.1645. Min Act: -0.1700
Data Index: 3502073 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0395. Min Range: -8.0395
Max Act: 7.1645. Min Act: -0.1700
Data Index: 5237587 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19