Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5069 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.5778. Min Act: -0.1700
Data Index: 4123384 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.1091. Min Act: -0.1700
Data Index: 4707339 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0778. Min Act: -0.1700
Data Index: 442292 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0153. Min Act: -0.1700
Data Index: 935466 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0778. Min Act: -0.1700
Data Index: 6936839 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0466. Min Act: -0.1700
Data Index: 5163637 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0466. Min Act: -0.1700
Data Index: 3058099 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0153. Min Act: -0.1700
Data Index: 3564387 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0153. Min Act: -0.1700
Data Index: 6947864 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0153. Min Act: -0.1700
Data Index: 4368743 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0153. Min Act: -0.1700
Data Index: 3789809 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5778. Min Range: -5.5778
Max Act: 4.9841. Min Act: -0.1700
Data Index: 8048899 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5778. Min Range: -5.5778
Max Act: 4.9841. Min Act: -0.1700
Data Index: 5863190 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5778. Min Range: -5.5778
Max Act: 4.9841. Min Act: -0.1700
Data Index: 7781711 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5778. Min Range: -5.5778
Max Act: 4.9841. Min Act: -0.1700
Data Index: 2704865 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5778. Min Range: -5.5778
Max Act: 4.9841. Min Act: -0.1700
Data Index: 2905287 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5778. Min Range: -5.5778
Max Act: 4.9841. Min Act: -0.1700
Data Index: 4567811 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5778. Min Range: -5.5778
Max Act: 4.9841. Min Act: -0.1700
Data Index: 1848780 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5778. Min Range: -5.5778
Max Act: 4.9528. Min Act: -0.1700
Data Index: 279346 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5778. Min Range: -5.5778
Max Act: 4.9216. Min Act: -0.1700
Data Index: 3618958 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19