Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 348 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1688. Min Range: -4.1688
Max Act: 4.1688. Min Act: -0.1700
Data Index: 2643757 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1688. Min Range: -4.1688
Max Act: 4.1688. Min Act: -0.1700
Data Index: 2643758 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1688. Min Range: -4.1688
Max Act: 4.0437. Min Act: -0.1700
Data Index: 3543285 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1688. Min Range: -4.1688
Max Act: 4.0125. Min Act: -0.1700
Data Index: 7498260 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.8562. Min Act: -0.1700
Data Index: 6034311 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.8249. Min Act: -0.1700
Data Index: 29385 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.8249. Min Act: -0.1700
Data Index: 8200113 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.8249. Min Act: -0.1700
Data Index: 3508470 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.7936. Min Act: -0.1700
Data Index: 4800547 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.7623. Min Act: -0.1700
Data Index: 8564388 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.7936. Min Act: -0.1700
Data Index: 559458 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.7936. Min Act: -0.1700
Data Index: 3688708 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.7623. Min Act: -0.1700
Data Index: 6659324 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.7623. Min Act: -0.1700
Data Index: 6705118 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.7311. Min Act: -0.1700
Data Index: 7769216 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.7311. Min Act: -0.1700
Data Index: 4336899 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.7311. Min Act: -0.1700
Data Index: 3854051 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.7311. Min Act: -0.1700
Data Index: 192614 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.7311. Min Act: -0.1700
Data Index: 29386 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1688. Min Range: -4.1688
Max Act: 3.6685. Min Act: -0.1700
Data Index: 6163035 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19