Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1226 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1142. Min Range: -5.1142
Max Act: 5.1142. Min Act: -0.1700
Data Index: 973079 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1142. Min Range: -5.1142
Max Act: 5.0517. Min Act: -0.1700
Data Index: 6212036 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.9580. Min Act: -0.1700
Data Index: 6008055 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.8330. Min Act: -0.1700
Data Index: 7278751 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.8642. Min Act: -0.1700
Data Index: 5676286 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.8642. Min Act: -0.1700
Data Index: 2096731 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.8017. Min Act: -0.1700
Data Index: 6918728 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.8330. Min Act: -0.1700
Data Index: 5070342 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.8330. Min Act: -0.1700
Data Index: 5932291 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.8330. Min Act: -0.1700
Data Index: 8216256 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.8017. Min Act: -0.1700
Data Index: 2078363 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.8017. Min Act: -0.1700
Data Index: 3219380 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.8017. Min Act: -0.1700
Data Index: 8203551 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.7705. Min Act: -0.1700
Data Index: 5781121 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.7705. Min Act: -0.1700
Data Index: 5000733 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.7705. Min Act: -0.1700
Data Index: 4246080 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.8017. Min Act: -0.1700
Data Index: 6120696 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.7705. Min Act: -0.1700
Data Index: 5636325 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.8017. Min Act: -0.1700
Data Index: 7051996 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1142. Min Range: -5.1142
Max Act: 4.7392. Min Act: -0.1700
Data Index: 5623524 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19