Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1656. Min Range: -4.1656
Max Act: 4.1656. Min Act: -0.1700
Data Index: 2477076 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1656. Min Range: -4.1656
Max Act: 4.0718. Min Act: -0.1700
Data Index: 6325133 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1656. Min Range: -4.1656
Max Act: 4.0093. Min Act: -0.1700
Data Index: 7015707 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1656. Min Range: -4.1656
Max Act: 4.0406. Min Act: -0.1700
Data Index: 3043491 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1656. Min Range: -4.1656
Max Act: 4.0093. Min Act: -0.1700
Data Index: 957860 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1656. Min Range: -4.1656
Max Act: 4.0093. Min Act: -0.1700
Data Index: 226071 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.9780. Min Act: -0.1700
Data Index: 6643382 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.9780. Min Act: -0.1700
Data Index: 1857302 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.9780. Min Act: -0.1700
Data Index: 2354023 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.9780. Min Act: -0.1700
Data Index: 255387 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.9780. Min Act: -0.1700
Data Index: 4381900 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.9468. Min Act: -0.1700
Data Index: 476489 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.9780. Min Act: -0.1700
Data Index: 8585339 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.9468. Min Act: -0.1700
Data Index: 2077371 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.8843. Min Act: -0.1700
Data Index: 7497696 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.9155. Min Act: -0.1700
Data Index: 3445019 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.9155. Min Act: -0.1700
Data Index: 7065876 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.8843. Min Act: -0.1700
Data Index: 2215824 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.8843. Min Act: -0.1700
Data Index: 6262260 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1656. Min Range: -4.1656
Max Act: 3.8843. Min Act: -0.1700
Data Index: 957867 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19