Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 488 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.6695. Min Act: -0.1700
Data Index: 2500360 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.6070. Min Act: -0.1700
Data Index: 2140167 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.5445. Min Act: -0.1700
Data Index: 6585807 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.4820. Min Act: -0.1700
Data Index: 8083443 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3570. Min Act: -0.1700
Data Index: 8273031 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3883. Min Act: -0.1700
Data Index: 7526405 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3570. Min Act: -0.1700
Data Index: 1983486 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3570. Min Act: -0.1700
Data Index: 1144694 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3570. Min Act: -0.1700
Data Index: 4612634 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3570. Min Act: -0.1700
Data Index: 6290471 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3570. Min Act: -0.1700
Data Index: 1758575 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3258. Min Act: -0.1700
Data Index: 1877430 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3258. Min Act: -0.1700
Data Index: 2071059 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3258. Min Act: -0.1700
Data Index: 8146034 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3258. Min Act: -0.1700
Data Index: 7925168 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3258. Min Act: -0.1700
Data Index: 594028 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3258. Min Act: -0.1700
Data Index: 478360 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2945. Min Act: -0.1700
Data Index: 1499785 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2945. Min Act: -0.1700
Data Index: 2266767 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2633. Min Act: -0.1700
Data Index: 5071035 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19