Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3315. Min Range: -11.3315
Max Act: 11.3315. Min Act: -0.1700
Data Index: 2184130 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.7065. Min Act: -0.1700
Data Index: 6439887 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.7065. Min Act: -0.1700
Data Index: 7560027 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.6440. Min Act: -0.1700
Data Index: 1029873 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.5190. Min Act: -0.1700
Data Index: 396559 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.5190. Min Act: -0.1700
Data Index: 5469401 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.5190. Min Act: -0.1700
Data Index: 6150401 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.4565. Min Act: -0.1700
Data Index: 4243036 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.4565. Min Act: -0.1700
Data Index: 2086466 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.3940. Min Act: -0.1700
Data Index: 4534795 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.3940. Min Act: -0.1700
Data Index: 4357506 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.3940. Min Act: -0.1700
Data Index: 2486026 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.3315. Min Act: -0.1700
Data Index: 518160 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.2690. Min Act: -0.1700
Data Index: 7228536 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.2690. Min Act: -0.1700
Data Index: 463225 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.3315. Min Act: -0.1700
Data Index: 2116673 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.2690. Min Act: -0.1700
Data Index: 5862641 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.2065. Min Act: -0.1700
Data Index: 1298314 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.2690. Min Act: -0.1700
Data Index: 4847006 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3315. Min Range: -11.3315
Max Act: 10.2065. Min Act: -0.1700
Data Index: 7525553 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19