Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2699 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.4407. Min Act: -0.1700
Data Index: 6833409 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.4094. Min Act: -0.1700
Data Index: 65971 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.4094. Min Act: -0.1700
Data Index: 1983519 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.3469. Min Act: -0.1700
Data Index: 1423820 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.3469. Min Act: -0.1700
Data Index: 105042 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.3469. Min Act: -0.1700
Data Index: 3163367 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.3157. Min Act: -0.1700
Data Index: 2700453 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.3157. Min Act: -0.1700
Data Index: 2517652 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.3157. Min Act: -0.1700
Data Index: 3021425 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.2844. Min Act: -0.1700
Data Index: 1938414 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.2532. Min Act: -0.1700
Data Index: 8802773 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.2844. Min Act: -0.1700
Data Index: 4870243 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.2844. Min Act: -0.1700
Data Index: 8591771 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.2844. Min Act: -0.1700
Data Index: 1485388 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.2532. Min Act: -0.1700
Data Index: 1940710 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.2532. Min Act: -0.1700
Data Index: 8591770 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.2219. Min Act: -0.1700
Data Index: 2415623 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.2219. Min Act: -0.1700
Data Index: 4310626 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.2219. Min Act: -0.1700
Data Index: 4374301 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4407. Min Range: -5.4407
Max Act: 5.1594. Min Act: -0.1700
Data Index: 6523398 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19