Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3696. Min Range: -5.3696
Max Act: 5.3696. Min Act: -0.1700
Data Index: 8033076 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3696. Min Range: -5.3696
Max Act: 5.0571. Min Act: -0.1700
Data Index: 873153 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3696. Min Range: -5.3696
Max Act: 5.0258. Min Act: -0.1700
Data Index: 4378690 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.8696. Min Act: -0.1700
Data Index: 5914362 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.8696. Min Act: -0.1700
Data Index: 417261 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.7133. Min Act: -0.1700
Data Index: 1994037 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.6508. Min Act: -0.1700
Data Index: 3777917 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.6821. Min Act: -0.1700
Data Index: 4086512 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.5883. Min Act: -0.1700
Data Index: 3775203 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.5571. Min Act: -0.1700
Data Index: 8447025 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.5571. Min Act: -0.1700
Data Index: 6367203 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.4946. Min Act: -0.1700
Data Index: 4404115 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.4946. Min Act: -0.1700
Data Index: 6229333 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.4633. Min Act: -0.1700
Data Index: 3995168 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.4321. Min Act: -0.1700
Data Index: 2034839 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.4321. Min Act: -0.1700
Data Index: 417264 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.4321. Min Act: -0.1700
Data Index: 417260 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.4321. Min Act: -0.1700
Data Index: 2580842 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.4321. Min Act: -0.1700
Data Index: 7059372 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3696. Min Range: -5.3696
Max Act: 4.4321. Min Act: -0.1700
Data Index: 2677103 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19