Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1733 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.5384. Min Act: -0.1700
Data Index: 803115 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.4134. Min Act: -0.1700
Data Index: 8552750 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.3197. Min Act: -0.1700
Data Index: 7085076 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.2259. Min Act: -0.1700
Data Index: 3227999 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.2259. Min Act: -0.1700
Data Index: 2333373 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1947. Min Act: -0.1700
Data Index: 4103320 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.2259. Min Act: -0.1700
Data Index: 7568142 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1947. Min Act: -0.1700
Data Index: 7820103 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1947. Min Act: -0.1700
Data Index: 2918432 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1634. Min Act: -0.1700
Data Index: 6614093 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1322. Min Act: -0.1700
Data Index: 2171933 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1009. Min Act: -0.1700
Data Index: 6420081 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1009. Min Act: -0.1700
Data Index: 2348340 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.1009. Min Act: -0.1700
Data Index: 2152770 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.0697. Min Act: -0.1700
Data Index: 2137646 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.0384. Min Act: -0.1700
Data Index: 3078748 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.0384. Min Act: -0.1700
Data Index: 2655867 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.0384. Min Act: -0.1700
Data Index: 6872664 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.0384. Min Act: -0.1700
Data Index: 872527 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5384. Min Range: -5.5384
Max Act: 5.0384. Min Act: -0.1700
Data Index: 6037954 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19