Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 652 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4799. Min Range: -9.4799
Max Act: 9.4799. Min Act: -0.1700
Data Index: 3924948 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4799. Min Range: -9.4799
Max Act: 9.4799. Min Act: -0.1700
Data Index: 6675091 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.9174. Min Act: -0.1700
Data Index: 5167299 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.7299. Min Act: -0.1700
Data Index: 8808615 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.7924. Min Act: -0.1700
Data Index: 3469387 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.6674. Min Act: -0.1700
Data Index: 5916887 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.7299. Min Act: -0.1700
Data Index: 5697866 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.7924. Min Act: -0.1700
Data Index: 8234819 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.6674. Min Act: -0.1700
Data Index: 2700949 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.5424. Min Act: -0.1700
Data Index: 4465510 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.6049. Min Act: -0.1700
Data Index: 5760677 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.6049. Min Act: -0.1700
Data Index: 4600577 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.6049. Min Act: -0.1700
Data Index: 4330483 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.6049. Min Act: -0.1700
Data Index: 449939 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.4799. Min Act: -0.1700
Data Index: 945986 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.3549. Min Act: -0.1700
Data Index: 1208627 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.4174. Min Act: -0.1700
Data Index: 1202925 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.3549. Min Act: -0.1700
Data Index: 1386437 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.4174. Min Act: -0.1700
Data Index: 5466910 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4799. Min Range: -9.4799
Max Act: 8.4174. Min Act: -0.1700
Data Index: 3366408 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19