Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4806 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.3293. Min Act: -0.1700
Data Index: 5084712 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.2668. Min Act: -0.1700
Data Index: 3904040 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.2668. Min Act: -0.1700
Data Index: 1619071 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.1418. Min Act: -0.1700
Data Index: 5097438 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.1418. Min Act: -0.1700
Data Index: 3955777 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.2043. Min Act: -0.1700
Data Index: 3188517 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.0793. Min Act: -0.1700
Data Index: 7760046 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.0793. Min Act: -0.1700
Data Index: 403679 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.0793. Min Act: -0.1700
Data Index: 5367244 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.0168. Min Act: -0.1700
Data Index: 3272849 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.0168. Min Act: -0.1700
Data Index: 4726555 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.0793. Min Act: -0.1700
Data Index: 4234309 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3293. Min Range: -9.3293
Max Act: 8.9543. Min Act: -0.1700
Data Index: 2429674 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3293. Min Range: -9.3293
Max Act: 9.0168. Min Act: -0.1700
Data Index: 4158051 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3293. Min Range: -9.3293
Max Act: 8.9543. Min Act: -0.1700
Data Index: 880381 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3293. Min Range: -9.3293
Max Act: 8.9543. Min Act: -0.1700
Data Index: 7401010 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3293. Min Range: -9.3293
Max Act: 8.9543. Min Act: -0.1700
Data Index: 4013559 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3293. Min Range: -9.3293
Max Act: 8.9543. Min Act: -0.1700
Data Index: 4873501 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3293. Min Range: -9.3293
Max Act: 8.8918. Min Act: -0.1700
Data Index: 2595725 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3293. Min Range: -9.3293
Max Act: 8.8918. Min Act: -0.1700
Data Index: 5356236 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19