Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5838 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.5487. Min Act: -0.1700
Data Index: 8306753 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.4862. Min Act: -0.1700
Data Index: 6844298 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.4237. Min Act: -0.1700
Data Index: 235347 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.3612. Min Act: -0.1700
Data Index: 5680915 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.3612. Min Act: -0.1700
Data Index: 7553613 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.2362. Min Act: -0.1700
Data Index: 2989364 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.2987. Min Act: -0.1700
Data Index: 7661365 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.2362. Min Act: -0.1700
Data Index: 2884103 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.1737. Min Act: -0.1700
Data Index: 2182263 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.1112. Min Act: -0.1700
Data Index: 5183326 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.0487. Min Act: -0.1700
Data Index: 7060757 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.0487. Min Act: -0.1700
Data Index: 8484408 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5487. Min Range: -9.5487
Max Act: 9.0487. Min Act: -0.1700
Data Index: 7498158 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5487. Min Range: -9.5487
Max Act: 8.9862. Min Act: -0.1700
Data Index: 4376564 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5487. Min Range: -9.5487
Max Act: 8.9237. Min Act: -0.1700
Data Index: 45836 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5487. Min Range: -9.5487
Max Act: 8.8612. Min Act: -0.1700
Data Index: 983434 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5487. Min Range: -9.5487
Max Act: 8.9237. Min Act: -0.1700
Data Index: 7161770 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5487. Min Range: -9.5487
Max Act: 8.9237. Min Act: -0.1700
Data Index: 5694651 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5487. Min Range: -9.5487
Max Act: 8.8612. Min Act: -0.1700
Data Index: 6841520 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5487. Min Range: -9.5487
Max Act: 8.8612. Min Act: -0.1700
Data Index: 7204226 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19