Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.4976. Min Act: -0.1700
Data Index: 2020532 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.4663. Min Act: -0.1700
Data Index: 2495857 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.4506. Min Act: -0.1700
Data Index: 5395097 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.4192. Min Act: -0.1700
Data Index: 6338165 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.4192. Min Act: -0.1700
Data Index: 8411453 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.4349. Min Act: -0.1700
Data Index: 2065860 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.4192. Min Act: -0.1700
Data Index: 2020536 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.4036. Min Act: -0.1700
Data Index: 649506 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.3408. Min Act: -0.1700
Data Index: 3106341 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.3408. Min Act: -0.1700
Data Index: 2412037 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.3408. Min Act: -0.1700
Data Index: 1025456 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.3408. Min Act: -0.1700
Data Index: 4103842 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.3408. Min Act: -0.1700
Data Index: 6576619 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.3251. Min Act: -0.1700
Data Index: 6747710 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.3094. Min Act: -0.1700
Data Index: 750044 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.3094. Min Act: -0.1700
Data Index: 2292967 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.3251. Min Act: -0.1700
Data Index: 2020537 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.2938. Min Act: -0.1700
Data Index: 6890264 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.2938. Min Act: -0.1700
Data Index: 6010034 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4976. Min Range: -3.4976
Max Act: 3.2938. Min Act: -0.1700
Data Index: 160762 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19