Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.3487. Min Act: -0.1700
Data Index: 4799208 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.3799. Min Act: -0.1700
Data Index: 2408278 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.3487. Min Act: -0.1700
Data Index: 3455405 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.3487. Min Act: -0.1700
Data Index: 6486253 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.2549. Min Act: -0.1700
Data Index: 1903811 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.1924. Min Act: -0.1700
Data Index: 1885120 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.1924. Min Act: -0.1700
Data Index: 3320624 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.1924. Min Act: -0.1700
Data Index: 2416034 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.1299. Min Act: -0.1700
Data Index: 6099323 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.0987. Min Act: -0.1700
Data Index: 7341613 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.0674. Min Act: -0.1700
Data Index: 1089420 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.0049. Min Act: -0.1700
Data Index: 4258171 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3799. Min Range: -7.3799
Max Act: 7.0049. Min Act: -0.1700
Data Index: 7569933 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3799. Min Range: -7.3799
Max Act: 6.9424. Min Act: -0.1700
Data Index: 6722234 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3799. Min Range: -7.3799
Max Act: 6.9112. Min Act: -0.1700
Data Index: 269498 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3799. Min Range: -7.3799
Max Act: 6.9424. Min Act: -0.1700
Data Index: 5996502 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3799. Min Range: -7.3799
Max Act: 6.9737. Min Act: -0.1700
Data Index: 4445269 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3799. Min Range: -7.3799
Max Act: 6.8799. Min Act: -0.1700
Data Index: 3120487 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3799. Min Range: -7.3799
Max Act: 6.9112. Min Act: -0.1700
Data Index: 721271 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3799. Min Range: -7.3799
Max Act: 6.9424. Min Act: -0.1700
Data Index: 5016020 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19