Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 668 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.4524. Min Act: -0.1700
Data Index: 1905126 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.4524. Min Act: -0.1699
Data Index: 877005 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.4700. Min Act: -0.1641
Data Index: 1543025 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.4524. Min Act: -0.1700
Data Index: 7295235 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.4700. Min Act: -0.1641
Data Index: 4631576 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.4524. Min Act: -0.1699
Data Index: 5723559 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.4700. Min Act: -0.1698
Data Index: 4389920 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.4524. Min Act: -0.1699
Data Index: 3267700 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.4524. Min Act: -0.1690
Data Index: 4149045 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.4348. Min Act: -0.1695
Data Index: 6891057 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.4348. Min Act: -0.1699
Data Index: 8319325 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.3819. Min Act: -0.1673
Data Index: 3611898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.3819. Min Act: -0.1673
Data Index: 2231855 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.3819. Min Act: -0.1673
Data Index: 891663 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.3819. Min Act: -0.1697
Data Index: 7213221 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.3467. Min Act: -0.1700
Data Index: 8492558 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.3467. Min Act: -0.1700
Data Index: 7713313 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.3114. Min Act: -0.1641
Data Index: 135180 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.3114. Min Act: -0.1666
Data Index: 1740630 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4700. Min Range: -1.4700
Max Act: 1.3114. Min Act: -0.1694
Data Index: 4345834 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19