Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3369 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.6586. Min Act: -0.1700
Data Index: 4275264 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.6586. Min Act: -0.1700
Data Index: 6123756 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.5336. Min Act: -0.1700
Data Index: 826236 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.4086. Min Act: -0.1700
Data Index: 1309312 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.4711. Min Act: -0.1700
Data Index: 8044526 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.4711. Min Act: -0.1700
Data Index: 5043607 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.3461. Min Act: -0.1700
Data Index: 6800435 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.3461. Min Act: -0.1700
Data Index: 4984135 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.3461. Min Act: -0.1700
Data Index: 4501625 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.2836. Min Act: -0.1700
Data Index: 2656737 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.3461. Min Act: -0.1700
Data Index: 21796 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.2836. Min Act: -0.1700
Data Index: 1062739 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.2211. Min Act: -0.1700
Data Index: 502331 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.2211. Min Act: -0.1700
Data Index: 5250898 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.2211. Min Act: -0.1700
Data Index: 6833969 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.2211. Min Act: -0.1700
Data Index: 7046394 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.2211. Min Act: -0.1700
Data Index: 1107132 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.1586. Min Act: -0.1700
Data Index: 3787480 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.0961. Min Act: -0.1700
Data Index: 3234358 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6586. Min Range: -8.6586
Max Act: 8.1586. Min Act: -0.1700
Data Index: 7919477 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19