Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0535. Min Range: -8.0535
Max Act: 8.0535. Min Act: -0.1700
Data Index: 1808573 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0535. Min Range: -8.0535
Max Act: 8.0222. Min Act: -0.1700
Data Index: 4386017 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.9285. Min Act: -0.1700
Data Index: 1424805 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.8660. Min Act: -0.1700
Data Index: 7823208 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.8660. Min Act: -0.1700
Data Index: 4686391 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.8035. Min Act: -0.1700
Data Index: 5125856 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.7722. Min Act: -0.1700
Data Index: 1424806 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.7410. Min Act: -0.1700
Data Index: 5125854 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.7410. Min Act: -0.1700
Data Index: 273845 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.7410. Min Act: -0.1700
Data Index: 4805278 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.6160. Min Act: -0.1700
Data Index: 5125858 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.5847. Min Act: -0.1700
Data Index: 7861684 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.5535. Min Act: -0.1700
Data Index: 8284757 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.5222. Min Act: -0.1700
Data Index: 8055032 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.5222. Min Act: -0.1700
Data Index: 3328573 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.3972. Min Act: -0.1700
Data Index: 5125852 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.3972. Min Act: -0.1700
Data Index: 5314029 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.3347. Min Act: -0.1700
Data Index: 2757578 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.3660. Min Act: -0.1700
Data Index: 5681650 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0535. Min Range: -8.0535
Max Act: 7.2722. Min Act: -0.1700
Data Index: 1385136 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19