Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2994 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.8663. Min Act: -0.1696
Data Index: 4201978 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.7459. Min Act: -0.1661
Data Index: 5078257 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.5895. Min Act: -0.1684
Data Index: 4537192 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.5720. Min Act: -0.1700
Data Index: 4951960 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.5194. Min Act: -0.1662
Data Index: 7589476 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.5194. Min Act: -0.1700
Data Index: 8123559 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.4843. Min Act: -0.1687
Data Index: 6299324 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.4843. Min Act: -0.1594
Data Index: 6310306 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.4492. Min Act: -0.1683
Data Index: 3574134 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.4316. Min Act: -0.1646
Data Index: 242196 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.4492. Min Act: -0.1699
Data Index: 5279526 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.4492. Min Act: -0.1699
Data Index: 1616344 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.4492. Min Act: -0.1700
Data Index: 1822461 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.4139. Min Act: -0.1687
Data Index: 152362 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.4316. Min Act: -0.1699
Data Index: 5373287 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.3963. Min Act: -0.1551
Data Index: 8641752 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.3963. Min Act: -0.1687
Data Index: 551856 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.3787. Min Act: -0.1700
Data Index: 4951961 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.3963. Min Act: -0.1696
Data Index: 1305823 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8663. Min Range: -1.8663
Max Act: 1.3787. Min Act: -0.1700
Data Index: 1551220 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19