Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1628 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1166. Min Range: -6.1166
Max Act: 6.1166. Min Act: -0.1700
Data Index: 3223880 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1166. Min Range: -6.1166
Max Act: 6.0854. Min Act: -0.1700
Data Index: 1416034 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1166. Min Range: -6.1166
Max Act: 6.0854. Min Act: -0.1700
Data Index: 8548689 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1166. Min Range: -6.1166
Max Act: 6.0541. Min Act: -0.1700
Data Index: 3610019 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1166. Min Range: -6.1166
Max Act: 6.0229. Min Act: -0.1700
Data Index: 2960974 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1166. Min Range: -6.1166
Max Act: 6.0541. Min Act: -0.1700
Data Index: 3177002 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9916. Min Act: -0.1700
Data Index: 3792814 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9916. Min Act: -0.1700
Data Index: 7603434 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9916. Min Act: -0.1700
Data Index: 2092736 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9916. Min Act: -0.1700
Data Index: 6363609 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9916. Min Act: -0.1700
Data Index: 8107114 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9604. Min Act: -0.1700
Data Index: 2427068 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9604. Min Act: -0.1700
Data Index: 2125463 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9604. Min Act: -0.1700
Data Index: 5776353 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9291. Min Act: -0.1700
Data Index: 5076315 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9291. Min Act: -0.1700
Data Index: 4200103 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9291. Min Act: -0.1700
Data Index: 4128530 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9291. Min Act: -0.1700
Data Index: 1080759 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9291. Min Act: -0.1700
Data Index: 4128532 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1166. Min Range: -6.1166
Max Act: 5.9291. Min Act: -0.1700
Data Index: 8005002 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19