Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1686 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.9413. Min Act: -0.1700
Data Index: 5768948 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.8476. Min Act: -0.1700
Data Index: 3859122 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.6601. Min Act: -0.1700
Data Index: 7466058 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.4413. Min Act: -0.1700
Data Index: 4476722 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.4726. Min Act: -0.1700
Data Index: 1623794 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.3163. Min Act: -0.1700
Data Index: 2198827 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.1913. Min Act: -0.1700
Data Index: 7715489 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.1288. Min Act: -0.1700
Data Index: 5666701 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.1601. Min Act: -0.1700
Data Index: 4832176 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.1288. Min Act: -0.1700
Data Index: 1754104 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.0976. Min Act: -0.1700
Data Index: 4780830 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.0663. Min Act: -0.1700
Data Index: 767147 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9413. Min Range: -6.9413
Max Act: 6.0351. Min Act: -0.1700
Data Index: 8528699 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9413. Min Range: -6.9413
Max Act: 5.9726. Min Act: -0.1700
Data Index: 5697652 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9413. Min Range: -6.9413
Max Act: 5.9726. Min Act: -0.1700
Data Index: 5980375 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9413. Min Range: -6.9413
Max Act: 5.9101. Min Act: -0.1700
Data Index: 6777275 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9413. Min Range: -6.9413
Max Act: 5.9413. Min Act: -0.1700
Data Index: 8215277 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9413. Min Range: -6.9413
Max Act: 5.9101. Min Act: -0.1700
Data Index: 2467002 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9413. Min Range: -6.9413
Max Act: 5.9101. Min Act: -0.1700
Data Index: 1074371 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9413. Min Range: -6.9413
Max Act: 5.9101. Min Act: -0.1700
Data Index: 6740892 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19