Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2050 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1567. Min Range: -6.1567
Max Act: 6.1567. Min Act: -0.1700
Data Index: 5853443 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1567. Min Range: -6.1567
Max Act: 6.0942. Min Act: -0.1700
Data Index: 832470 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1567. Min Range: -6.1567
Max Act: 6.0630. Min Act: -0.1700
Data Index: 3919108 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1567. Min Range: -6.1567
Max Act: 6.0005. Min Act: -0.1700
Data Index: 6340050 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.8755. Min Act: -0.1700
Data Index: 2176715 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.8442. Min Act: -0.1700
Data Index: 110217 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.7192. Min Act: -0.1700
Data Index: 4384671 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.7505. Min Act: -0.1700
Data Index: 1069129 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.6567. Min Act: -0.1700
Data Index: 543688 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.6255. Min Act: -0.1700
Data Index: 5273069 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.6255. Min Act: -0.1700
Data Index: 2609448 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.5942. Min Act: -0.1700
Data Index: 2433509 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.6255. Min Act: -0.1700
Data Index: 4542754 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.5942. Min Act: -0.1700
Data Index: 2509609 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.5942. Min Act: -0.1700
Data Index: 7746812 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.5630. Min Act: -0.1700
Data Index: 2045798 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.5630. Min Act: -0.1700
Data Index: 286940 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.5317. Min Act: -0.1700
Data Index: 5167652 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.4692. Min Act: -0.1700
Data Index: 3634900 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1567. Min Range: -6.1567
Max Act: 5.5005. Min Act: -0.1700
Data Index: 265317 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19