Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2703 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.4370. Min Act: -0.1700
Data Index: 5836854 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.3745. Min Act: -0.1700
Data Index: 16329 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.3745. Min Act: -0.1700
Data Index: 5758883 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.3432. Min Act: -0.1700
Data Index: 7346745 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.3120. Min Act: -0.1700
Data Index: 2187093 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.3120. Min Act: -0.1700
Data Index: 207139 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.3120. Min Act: -0.1700
Data Index: 2850620 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.3120. Min Act: -0.1700
Data Index: 1051685 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.3120. Min Act: -0.1700
Data Index: 118442 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.2807. Min Act: -0.1700
Data Index: 743473 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.2807. Min Act: -0.1700
Data Index: 5553202 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.2495. Min Act: -0.1700
Data Index: 2138979 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.2182. Min Act: -0.1700
Data Index: 6141312 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.2495. Min Act: -0.1700
Data Index: 8130785 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.2495. Min Act: -0.1700
Data Index: 4512393 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.2495. Min Act: -0.1700
Data Index: 7653887 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.2495. Min Act: -0.1700
Data Index: 3078075 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.2182. Min Act: -0.1700
Data Index: 6798484 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.2182. Min Act: -0.1700
Data Index: 7150077 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4370. Min Range: -4.4370
Max Act: 4.2182. Min Act: -0.1700
Data Index: 2193019 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19