Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.4606. Min Act: -0.1700
Data Index: 2055420 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.3981. Min Act: -0.1700
Data Index: 5480911 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.3356. Min Act: -0.1700
Data Index: 4959608 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.3356. Min Act: -0.1700
Data Index: 8655122 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.3356. Min Act: -0.1700
Data Index: 7974271 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.3356. Min Act: -0.1700
Data Index: 70451 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.3043. Min Act: -0.1700
Data Index: 7571584 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.3043. Min Act: -0.1700
Data Index: 1163653 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.2731. Min Act: -0.1700
Data Index: 1684013 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.2731. Min Act: -0.1700
Data Index: 5112898 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.2731. Min Act: -0.1700
Data Index: 5736159 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.2731. Min Act: -0.1700
Data Index: 1987527 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.2731. Min Act: -0.1700
Data Index: 7070408 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.2418. Min Act: -0.1700
Data Index: 7085440 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.2418. Min Act: -0.1700
Data Index: 3702424 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.2105. Min Act: -0.1700
Data Index: 6683058 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.2105. Min Act: -0.1700
Data Index: 3009334 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.2105. Min Act: -0.1700
Data Index: 6824709 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.2105. Min Act: -0.1700
Data Index: 2004661 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4606. Min Range: -4.4606
Max Act: 4.2105. Min Act: -0.1700
Data Index: 1618742 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19