Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5832. Min Range: -6.5832
Max Act: 6.5832. Min Act: -0.1700
Data Index: 6245045 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5832. Min Range: -6.5832
Max Act: 6.3332. Min Act: -0.1700
Data Index: 6821844 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5832. Min Range: -6.5832
Max Act: 6.1457. Min Act: -0.1700
Data Index: 8624166 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5832. Min Range: -6.5832
Max Act: 6.1144. Min Act: -0.1700
Data Index: 3871159 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5832. Min Range: -6.5832
Max Act: 6.0207. Min Act: -0.1700
Data Index: 4805068 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.9894. Min Act: -0.1700
Data Index: 824215 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.9269. Min Act: -0.1700
Data Index: 1221865 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.8957. Min Act: -0.1700
Data Index: 1387598 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.9269. Min Act: -0.1700
Data Index: 1792625 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.9269. Min Act: -0.1700
Data Index: 5058081 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.9269. Min Act: -0.1700
Data Index: 4979106 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.8957. Min Act: -0.1700
Data Index: 1104969 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.8957. Min Act: -0.1700
Data Index: 7510085 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.8332. Min Act: -0.1700
Data Index: 5617923 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.8332. Min Act: -0.1700
Data Index: 3758443 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.7707. Min Act: -0.1700
Data Index: 6837411 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.7707. Min Act: -0.1700
Data Index: 1123500 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.7082. Min Act: -0.1700
Data Index: 3287359 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.7082. Min Act: -0.1700
Data Index: 87014 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5832. Min Range: -6.5832
Max Act: 5.7394. Min Act: -0.1700
Data Index: 216292 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19