Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3878 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4791. Min Range: -7.4791
Max Act: 7.4791. Min Act: -0.1700
Data Index: 1425217 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4791. Min Range: -7.4791
Max Act: 7.4479. Min Act: -0.1700
Data Index: 381141 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4791. Min Range: -7.4791
Max Act: 7.3541. Min Act: -0.1700
Data Index: 154925 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4791. Min Range: -7.4791
Max Act: 7.3229. Min Act: -0.1700
Data Index: 4035659 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4791. Min Range: -7.4791
Max Act: 7.1979. Min Act: -0.1700
Data Index: 4179675 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4791. Min Range: -7.4791
Max Act: 7.1354. Min Act: -0.1700
Data Index: 497165 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4791. Min Range: -7.4791
Max Act: 7.1041. Min Act: -0.1700
Data Index: 853601 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4791. Min Range: -7.4791
Max Act: 7.0729. Min Act: -0.1700
Data Index: 2971979 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4791. Min Range: -7.4791
Max Act: 7.0416. Min Act: -0.1700
Data Index: 346586 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4791. Min Range: -7.4791
Max Act: 6.9791. Min Act: -0.1700
Data Index: 2179272 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4791. Min Range: -7.4791
Max Act: 6.9791. Min Act: -0.1700
Data Index: 8579808 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4791. Min Range: -7.4791
Max Act: 6.9791. Min Act: -0.1700
Data Index: 2025698 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4791. Min Range: -7.4791
Max Act: 6.9166. Min Act: -0.1700
Data Index: 4987487 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4791. Min Range: -7.4791
Max Act: 6.9166. Min Act: -0.1700
Data Index: 2759758 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4791. Min Range: -7.4791
Max Act: 6.8854. Min Act: -0.1700
Data Index: 2558467 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4791. Min Range: -7.4791
Max Act: 6.8541. Min Act: -0.1700
Data Index: 6648952 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4791. Min Range: -7.4791
Max Act: 6.8541. Min Act: -0.1700
Data Index: 1167361 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4791. Min Range: -7.4791
Max Act: 6.8541. Min Act: -0.1700
Data Index: 3363669 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4791. Min Range: -7.4791
Max Act: 6.8541. Min Act: -0.1700
Data Index: 805228 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4791. Min Range: -7.4791
Max Act: 6.8541. Min Act: -0.1700
Data Index: 7222077 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19