Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4571 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.9160. Min Act: -0.1700
Data Index: 697997 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.9160. Min Act: -0.1700
Data Index: 6701705 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.8222. Min Act: -0.1700
Data Index: 1540012 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.7910. Min Act: -0.1700
Data Index: 2247494 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.7597. Min Act: -0.1700
Data Index: 8268662 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.7597. Min Act: -0.1700
Data Index: 2988651 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.6972. Min Act: -0.1700
Data Index: 1512866 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.6972. Min Act: -0.1700
Data Index: 3009799 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.6347. Min Act: -0.1700
Data Index: 7249387 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.6347. Min Act: -0.1700
Data Index: 6285299 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.6035. Min Act: -0.1700
Data Index: 3688486 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.6035. Min Act: -0.1700
Data Index: 6284898 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.6035. Min Act: -0.1700
Data Index: 2339194 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.6035. Min Act: -0.1700
Data Index: 6530823 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.6035. Min Act: -0.1700
Data Index: 7832645 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.6035. Min Act: -0.1700
Data Index: 7539168 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.6035. Min Act: -0.1700
Data Index: 225907 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.5410. Min Act: -0.1700
Data Index: 2496017 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.5722. Min Act: -0.1700
Data Index: 2385365 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9160. Min Range: -4.9160
Max Act: 4.6035. Min Act: -0.1700
Data Index: 4554211 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19