Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6074 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2488. Min Range: -11.2488
Max Act: 11.2488. Min Act: -0.1700
Data Index: 6461916 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2488. Min Range: -11.2488
Max Act: 11.1238. Min Act: -0.1700
Data Index: 410783 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2488. Min Range: -11.2488
Max Act: 11.0613. Min Act: -0.1700
Data Index: 8621391 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.8113. Min Act: -0.1700
Data Index: 4832088 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.8113. Min Act: -0.1700
Data Index: 3495905 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.7488. Min Act: -0.1700
Data Index: 6082597 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.7488. Min Act: -0.1700
Data Index: 3180366 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.6238. Min Act: -0.1700
Data Index: 4423745 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.6863. Min Act: -0.1700
Data Index: 3256291 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.6238. Min Act: -0.1700
Data Index: 4660522 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.6238. Min Act: -0.1700
Data Index: 6084703 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.6238. Min Act: -0.1700
Data Index: 3101387 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.6238. Min Act: -0.1700
Data Index: 3397791 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.5613. Min Act: -0.1700
Data Index: 2582622 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.5613. Min Act: -0.1700
Data Index: 2666889 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.4988. Min Act: -0.1700
Data Index: 398696 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.4988. Min Act: -0.1700
Data Index: 1922480 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.4363. Min Act: -0.1700
Data Index: 44190 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.4363. Min Act: -0.1700
Data Index: 245962 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2488. Min Range: -11.2488
Max Act: 10.4988. Min Act: -0.1700
Data Index: 5834516 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19