Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2434 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.5663. Min Act: -0.1700
Data Index: 310464 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.4726. Min Act: -0.1700
Data Index: 3826573 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.3163. Min Act: -0.1700
Data Index: 8353268 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.2851. Min Act: -0.1700
Data Index: 6611610 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.2226. Min Act: -0.1700
Data Index: 1497663 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.1913. Min Act: -0.1700
Data Index: 1788906 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.1913. Min Act: -0.1700
Data Index: 3563331 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.1913. Min Act: -0.1700
Data Index: 7443944 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.1601. Min Act: -0.1700
Data Index: 6585059 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.1601. Min Act: -0.1700
Data Index: 876871 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.1288. Min Act: -0.1700
Data Index: 2173729 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.1601. Min Act: -0.1700
Data Index: 5402584 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.0976. Min Act: -0.1700
Data Index: 4663223 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.0976. Min Act: -0.1700
Data Index: 8176211 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.0663. Min Act: -0.1700
Data Index: 2248580 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.0976. Min Act: -0.1700
Data Index: 4934792 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.0663. Min Act: -0.1700
Data Index: 5853742 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5663. Min Range: -7.5663
Max Act: 7.0038. Min Act: -0.1700
Data Index: 8715257 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5663. Min Range: -7.5663
Max Act: 6.9726. Min Act: -0.1700
Data Index: 7187151 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5663. Min Range: -7.5663
Max Act: 6.9726. Min Act: -0.1700
Data Index: 6561896 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19