Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2988 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2994. Min Range: -7.2994
Max Act: 7.2994. Min Act: -0.1700
Data Index: 4407332 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.7994. Min Act: -0.1700
Data Index: 1243346 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.5494. Min Act: -0.1700
Data Index: 364179 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.5494. Min Act: -0.1700
Data Index: 7128440 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.5181. Min Act: -0.1700
Data Index: 7567290 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.5181. Min Act: -0.1700
Data Index: 6792854 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.4869. Min Act: -0.1700
Data Index: 8066377 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.4869. Min Act: -0.1700
Data Index: 4482235 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.4244. Min Act: -0.1700
Data Index: 4001520 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.4244. Min Act: -0.1700
Data Index: 7583308 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.3931. Min Act: -0.1700
Data Index: 602702 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.3619. Min Act: -0.1700
Data Index: 1027908 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.3619. Min Act: -0.1700
Data Index: 6125497 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.3619. Min Act: -0.1700
Data Index: 1657871 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.3619. Min Act: -0.1700
Data Index: 748950 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.3306. Min Act: -0.1700
Data Index: 1862213 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.2994. Min Act: -0.1700
Data Index: 6890745 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.3306. Min Act: -0.1700
Data Index: 4774188 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.2994. Min Act: -0.1700
Data Index: 5345116 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2994. Min Range: -7.2994
Max Act: 6.2994. Min Act: -0.1700
Data Index: 6434086 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19