Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3735 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1102. Min Range: -2.1102
Max Act: 2.1102. Min Act: -0.1700
Data Index: 350567 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1102. Min Range: -2.1102
Max Act: 2.0262. Min Act: -0.1686
Data Index: 4856074 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1102. Min Range: -2.1102
Max Act: 2.0431. Min Act: -0.1471
Data Index: 7301622 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1102. Min Range: -2.1102
Max Act: 2.0093. Min Act: -0.1700
Data Index: 8589606 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1102. Min Range: -2.1102
Max Act: 2.0093. Min Act: -0.1410
Data Index: 2934792 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9755. Min Act: -0.1445
Data Index: 4050901 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9755. Min Act: -0.1700
Data Index: 1876385 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9586. Min Act: -0.1686
Data Index: 8642196 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9755. Min Act: -0.1678
Data Index: 4986786 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9755. Min Act: -0.1699
Data Index: 3535347 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9586. Min Act: -0.1681
Data Index: 5956273 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9586. Min Act: -0.1364
Data Index: 4146884 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9586. Min Act: -0.1112
Data Index: 4146880 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9416. Min Act: -0.1689
Data Index: 5099434 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9416. Min Act: -0.1700
Data Index: 2634618 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9416. Min Act: -0.1524
Data Index: 740521 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9416. Min Act: -0.1677
Data Index: 2179828 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9246. Min Act: -0.1674
Data Index: 2795129 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9246. Min Act: -0.1700
Data Index: 4187130 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1102. Min Range: -2.1102
Max Act: 1.9246. Min Act: -0.1700
Data Index: 6503406 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19