Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6012 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.3364. Min Act: -0.1700
Data Index: 3741936 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.2114. Min Act: -0.1700
Data Index: 6778882 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.2739. Min Act: -0.1700
Data Index: 3666797 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.2114. Min Act: -0.1700
Data Index: 2057278 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.0864. Min Act: -0.1700
Data Index: 1489775 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.0864. Min Act: -0.1700
Data Index: 2855969 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.0864. Min Act: -0.1700
Data Index: 7028199 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.0864. Min Act: -0.1700
Data Index: 7068683 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.0239. Min Act: -0.1700
Data Index: 6146171 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.0239. Min Act: -0.1700
Data Index: 4407805 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.0239. Min Act: -0.1700
Data Index: 357772 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.0239. Min Act: -0.1700
Data Index: 8372413 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.0239. Min Act: -0.1700
Data Index: 7479750 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.0239. Min Act: -0.1700
Data Index: 3202483 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.0239. Min Act: -0.1700
Data Index: 3930229 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3364. Min Range: -9.3364
Max Act: 8.8989. Min Act: -0.1700
Data Index: 3962141 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3364. Min Range: -9.3364
Max Act: 8.9614. Min Act: -0.1700
Data Index: 6151918 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3364. Min Range: -9.3364
Max Act: 9.0239. Min Act: -0.1700
Data Index: 7201592 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3364. Min Range: -9.3364
Max Act: 8.9614. Min Act: -0.1700
Data Index: 2869134 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3364. Min Range: -9.3364
Max Act: 8.9614. Min Act: -0.1700
Data Index: 7285114 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19