Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2827 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2583. Min Range: -8.2583
Max Act: 8.2583. Min Act: -0.1700
Data Index: 5165379 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2583. Min Range: -8.2583
Max Act: 8.0708. Min Act: -0.1700
Data Index: 2596561 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.8833. Min Act: -0.1700
Data Index: 5306638 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.8208. Min Act: -0.1700
Data Index: 4054921 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.5708. Min Act: -0.1700
Data Index: 6242980 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.6020. Min Act: -0.1700
Data Index: 7150931 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.5395. Min Act: -0.1700
Data Index: 5152990 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.4770. Min Act: -0.1700
Data Index: 6378081 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.3833. Min Act: -0.1700
Data Index: 8008472 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.4145. Min Act: -0.1700
Data Index: 2948802 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.3833. Min Act: -0.1700
Data Index: 5704881 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.3520. Min Act: -0.1700
Data Index: 3015847 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.3208. Min Act: -0.1700
Data Index: 1195495 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.3520. Min Act: -0.1700
Data Index: 2155643 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.3208. Min Act: -0.1700
Data Index: 3204174 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.3208. Min Act: -0.1700
Data Index: 4855941 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.2895. Min Act: -0.1700
Data Index: 6070143 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.2895. Min Act: -0.1700
Data Index: 63929 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.2895. Min Act: -0.1700
Data Index: 6897125 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2583. Min Range: -8.2583
Max Act: 7.2583. Min Act: -0.1700
Data Index: 3308901 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19