Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2636 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3769. Min Range: -6.3769
Max Act: 6.3769. Min Act: -0.1700
Data Index: 1449491 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3769. Min Range: -6.3769
Max Act: 6.1581. Min Act: -0.1700
Data Index: 396745 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3769. Min Range: -6.3769
Max Act: 6.1581. Min Act: -0.1700
Data Index: 3181611 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3769. Min Range: -6.3769
Max Act: 6.1581. Min Act: -0.1700
Data Index: 1455177 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3769. Min Range: -6.3769
Max Act: 6.0644. Min Act: -0.1700
Data Index: 4531253 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3769. Min Range: -6.3769
Max Act: 6.0956. Min Act: -0.1700
Data Index: 3842109 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.9706. Min Act: -0.1700
Data Index: 4045160 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.9706. Min Act: -0.1700
Data Index: 5979558 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.9394. Min Act: -0.1700
Data Index: 4172951 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.9081. Min Act: -0.1700
Data Index: 84860 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.7831. Min Act: -0.1700
Data Index: 3792265 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.8144. Min Act: -0.1700
Data Index: 7426939 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.7831. Min Act: -0.1700
Data Index: 5339664 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.7519. Min Act: -0.1700
Data Index: 4882705 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.7206. Min Act: -0.1700
Data Index: 1703640 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.6894. Min Act: -0.1700
Data Index: 3698361 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.6581. Min Act: -0.1700
Data Index: 4021366 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.5956. Min Act: -0.1700
Data Index: 1499417 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.6269. Min Act: -0.1700
Data Index: 3807977 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3769. Min Range: -6.3769
Max Act: 5.5956. Min Act: -0.1700
Data Index: 4152101 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19