Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3947 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1682. Min Range: -6.1682
Max Act: 6.1682. Min Act: -0.1700
Data Index: 6128046 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1682. Min Range: -6.1682
Max Act: 6.1682. Min Act: -0.1700
Data Index: 3367953 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1682. Min Range: -6.1682
Max Act: 6.1057. Min Act: -0.1700
Data Index: 821428 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1682. Min Range: -6.1682
Max Act: 6.1057. Min Act: -0.1700
Data Index: 3092693 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.9182. Min Act: -0.1700
Data Index: 1086192 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.9182. Min Act: -0.1700
Data Index: 276726 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.8869. Min Act: -0.1700
Data Index: 8487154 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.8557. Min Act: -0.1700
Data Index: 5910934 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.7932. Min Act: -0.1700
Data Index: 4852146 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.7932. Min Act: -0.1700
Data Index: 1973653 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.7307. Min Act: -0.1700
Data Index: 6317541 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.7307. Min Act: -0.1700
Data Index: 6680658 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.6682. Min Act: -0.1700
Data Index: 1246896 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.6369. Min Act: -0.1700
Data Index: 5591436 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.6682. Min Act: -0.1700
Data Index: 590452 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.6682. Min Act: -0.1700
Data Index: 6667052 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.6057. Min Act: -0.1700
Data Index: 6934378 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.6057. Min Act: -0.1700
Data Index: 3773827 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.5744. Min Act: -0.1700
Data Index: 7542078 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1682. Min Range: -6.1682
Max Act: 5.5744. Min Act: -0.1700
Data Index: 314145 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19