Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4917 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.7951. Min Act: -0.1700
Data Index: 297325 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.7639. Min Act: -0.1700
Data Index: 3214268 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.7014. Min Act: -0.1700
Data Index: 962757 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.6701. Min Act: -0.1700
Data Index: 4219144 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.4826. Min Act: -0.1700
Data Index: 7933996 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.4514. Min Act: -0.1700
Data Index: 6120384 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.3889. Min Act: -0.1700
Data Index: 3806425 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.4201. Min Act: -0.1700
Data Index: 3304699 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.3889. Min Act: -0.1700
Data Index: 2663510 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.3576. Min Act: -0.1700
Data Index: 6975222 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.3576. Min Act: -0.1700
Data Index: 4780656 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.3264. Min Act: -0.1700
Data Index: 1660838 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.2639. Min Act: -0.1700
Data Index: 1009685 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.2639. Min Act: -0.1700
Data Index: 2508659 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.2639. Min Act: -0.1700
Data Index: 7119940 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.2639. Min Act: -0.1700
Data Index: 3133692 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.2326. Min Act: -0.1700
Data Index: 4315971 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.2326. Min Act: -0.1700
Data Index: 5451615 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.2326. Min Act: -0.1700
Data Index: 5240263 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7951. Min Range: -5.7951
Max Act: 5.2014. Min Act: -0.1700
Data Index: 3775499 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19