Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2963 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6214. Min Range: -7.6214
Max Act: 7.6214. Min Act: -0.1700
Data Index: 5459332 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6214. Min Range: -7.6214
Max Act: 7.4026. Min Act: -0.1700
Data Index: 2175298 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6214. Min Range: -7.6214
Max Act: 7.1839. Min Act: -0.1700
Data Index: 3475088 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6214. Min Range: -7.6214
Max Act: 7.0589. Min Act: -0.1700
Data Index: 7949461 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6214. Min Range: -7.6214
Max Act: 7.0276. Min Act: -0.1700
Data Index: 1363859 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.9651. Min Act: -0.1700
Data Index: 7036472 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.8714. Min Act: -0.1700
Data Index: 2774601 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.8714. Min Act: -0.1700
Data Index: 5319060 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.8714. Min Act: -0.1700
Data Index: 4814443 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.8401. Min Act: -0.1700
Data Index: 4018892 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.7776. Min Act: -0.1700
Data Index: 6091933 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.8089. Min Act: -0.1700
Data Index: 3323715 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.8089. Min Act: -0.1700
Data Index: 4598399 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.8089. Min Act: -0.1700
Data Index: 3080744 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.7776. Min Act: -0.1699
Data Index: 8500309 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.7776. Min Act: -0.1700
Data Index: 6971974 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.7464. Min Act: -0.1700
Data Index: 5150436 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.7776. Min Act: -0.1699
Data Index: 2097703 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.7464. Min Act: -0.1700
Data Index: 4970329 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6214. Min Range: -7.6214
Max Act: 6.7464. Min Act: -0.1699
Data Index: 2596294 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19