Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6316 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0166. Min Range: -8.0166
Max Act: 8.0166. Min Act: -0.1700
Data Index: 4492257 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0166. Min Range: -8.0166
Max Act: 8.0166. Min Act: -0.1700
Data Index: 3691823 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.9541. Min Act: -0.1700
Data Index: 3754266 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.9541. Min Act: -0.1700
Data Index: 2423374 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.8916. Min Act: -0.1700
Data Index: 1628593 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.8291. Min Act: -0.1700
Data Index: 3661272 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.8291. Min Act: -0.1700
Data Index: 2101352 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.8291. Min Act: -0.1700
Data Index: 693399 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.7666. Min Act: -0.1700
Data Index: 7169406 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.7041. Min Act: -0.1700
Data Index: 5122242 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.7666. Min Act: -0.1700
Data Index: 4000150 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.7666. Min Act: -0.1700
Data Index: 4488924 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.7666. Min Act: -0.1700
Data Index: 857835 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.7041. Min Act: -0.1700
Data Index: 2472600 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.7041. Min Act: -0.1700
Data Index: 286124 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.7041. Min Act: -0.1700
Data Index: 4338908 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.7041. Min Act: -0.1700
Data Index: 3765790 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.7041. Min Act: -0.1700
Data Index: 3915985 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.7041. Min Act: -0.1700
Data Index: 1480846 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0166. Min Range: -8.0166
Max Act: 7.7041. Min Act: -0.1700
Data Index: 613181 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19