Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1707 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2723. Min Range: -7.2723
Max Act: 7.2723. Min Act: -0.1700
Data Index: 7690625 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2723. Min Range: -7.2723
Max Act: 7.2098. Min Act: -0.1700
Data Index: 4877905 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2723. Min Range: -7.2723
Max Act: 7.1473. Min Act: -0.1700
Data Index: 4101912 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2723. Min Range: -7.2723
Max Act: 7.1161. Min Act: -0.1700
Data Index: 7033261 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.9911. Min Act: -0.1700
Data Index: 3747149 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.8973. Min Act: -0.1700
Data Index: 2477020 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.8036. Min Act: -0.1700
Data Index: 6709960 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.8036. Min Act: -0.1700
Data Index: 3915186 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.7723. Min Act: -0.1700
Data Index: 8552120 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.7723. Min Act: -0.1700
Data Index: 5456484 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.7723. Min Act: -0.1700
Data Index: 3212215 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.7723. Min Act: -0.1700
Data Index: 2224809 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.7411. Min Act: -0.1700
Data Index: 3626642 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.7411. Min Act: -0.1700
Data Index: 2629719 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.7098. Min Act: -0.1700
Data Index: 3384588 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.7098. Min Act: -0.1700
Data Index: 7308795 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.6786. Min Act: -0.1700
Data Index: 3609430 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.6786. Min Act: -0.1700
Data Index: 8551318 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.6161. Min Act: -0.1700
Data Index: 1078684 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2723. Min Range: -7.2723
Max Act: 6.6473. Min Act: -0.1700
Data Index: 2999343 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19