Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2723. Min Range: -5.2723
Max Act: 5.2723. Min Act: -0.1700
Data Index: 7788297 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2723. Min Range: -5.2723
Max Act: 5.0536. Min Act: -0.1700
Data Index: 5302867 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.9911. Min Act: -0.1700
Data Index: 8536872 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.9911. Min Act: -0.1700
Data Index: 5636852 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.9286. Min Act: -0.1700
Data Index: 3196764 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8973. Min Act: -0.1700
Data Index: 2358553 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8661. Min Act: -0.1700
Data Index: 6103643 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8973. Min Act: -0.1700
Data Index: 1597007 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8661. Min Act: -0.1700
Data Index: 3196765 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8661. Min Act: -0.1700
Data Index: 927056 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8348. Min Act: -0.1700
Data Index: 4633407 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8348. Min Act: -0.1700
Data Index: 3196766 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8348. Min Act: -0.1700
Data Index: 4125270 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8348. Min Act: -0.1700
Data Index: 2687164 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8348. Min Act: -0.1700
Data Index: 334818 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8036. Min Act: -0.1700
Data Index: 1596146 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8036. Min Act: -0.1700
Data Index: 714034 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8036. Min Act: -0.1700
Data Index: 7421454 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.8036. Min Act: -0.1700
Data Index: 2086384 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2723. Min Range: -5.2723
Max Act: 4.7723. Min Act: -0.1700
Data Index: 3042507 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19